European Lighthouse on Secure and Safe AI

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Rezultaty

Benchmark Datasets

Six datasets and corresponding metrics will be defined, corresponding to the use cases.

Report on Privacy and Infrastructures Grand Challenge and Benchmarking Metrics

This report will summarise the results of Task 2.1.

Papers and Accompanying Code from Task 3.5 with New Methods and Open Source Tools

Papers and accompanying code from Task 3.5 with new methods and open source tools.

Report on Network and Communication Activities 2

Report on Network and Communication activities 2.

Intermediate Report on Privacy and Infrastructures

This report will consolidate progress on Tasks 2.2-2.4.

Report on Existing TPCA for Delivering AI Assurance 2: Journal Publication

This publication and D12 (D3.4) will summarise the findings on Task 3.3.

Report on Existing TPCA for Delivering AI Assurance 1: Policy Brief and Public Engagement Report

This publication and D13 (D3.5) will summarise the findings on Task 3.3.

Use Case Analysis Report

Detailed analysis of the six use cases, leading to specifications and requirements to be used as input to WP1-3.

Report on Technical Robustness and Safety Grand Challenge and Benchmarking Metrics

This report will summarise the results of Task 1.1.

Publish Strategic Research Agenda

Publish Strategic Research Agenda.

Report on Human-in-the-Loop Decision Making Grand Challenge

This report will summarise the results of Task 3.1.

Report on Results Based on SME Open Call

Report on results based on SME open call.

Report on Network and Communication Activities 3

Report on Network and Communication activities 3.

Report on Network and Communication Activities 1

Report on Network and Communication activities 1.

Report Detailing the Investigation and Framework from the Activities of Task 3.4

Report detailing the investigation and framework from the activities of Task 3.4.

Use Cases Activity Report 3

Updated version of D19 (D4.4).

New Methods for Interpretable-by-Design Deep Learning Methods

This publication will cover Task 3.2.

Use Cases Activity Report 1

Summary of progress on the implementation of demonstrators and benchmarks for each of the six use cases.

Use Cases Activity Report 2

Updated version of D18 (D4.3).

Intermediate Report on Technical Robustness and Safety

This report will consolidate progress on Tasks 1.2-1.5.

Software and Tools for Privacy-Preserving and Collaborative Learning

Release of open source software described in Task 2.5.

Software and Tools for Technical Robustness and Safety

Release of open source software described in Task 1.6.

Course Materials on Research Outcomes 1

Course materials on research outcomes 1.

Course Materials on Research Outcomes 2

Course materials on research outcomes 2.

Visual Identity, Style and Communication Guidelines

Visual identity, style and communication guidelines.

Publikacje

Towards algorithms and models that we can trust: A theoretical perspective

Autorzy: Luca Oneto, Sandro Ridella, Davide Anguita
Opublikowane w: Neurocomputing, Numer 592, 2024, ISSN 0925-2312
Wydawca: Elsevier BV
DOI: 10.1016/J.NEUCOM.2024.127798

Adversarial pruning: A survey and benchmark of pruning methods for adversarial robustness

Autorzy: Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio, Giorgio Giacinto, Fabio Roli
Opublikowane w: Pattern Recognition, Numer 168, 2025, ISSN 0031-3203
Wydawca: Elsevier BV
DOI: 10.1016/J.PATCOG.2025.111788

Informed Machine Learning: Excess risk and generalization

Autorzy: Luca Oneto, Sandro Ridella, Davide Anguita
Opublikowane w: Neurocomputing, Numer 646, 2025, ISSN 0925-2312
Wydawca: Elsevier BV
DOI: 10.1016/J.NEUCOM.2025.130521

Secml-Malware: Pentesting Windows Malware Classifiers with Adversarial Exemples in Python

Autorzy: Luca Demetrio, Battista Biggio
Opublikowane w: SSRN Electronic Journal, 2022, ISSN 1556-5068
Wydawca: Elsevier BV
DOI: 10.2139/SSRN.4066509

Foundation Models and Fine-Tuning: A Benchmark for Out of Distribution Detection

Autorzy: Francesco Cappio Borlino, Lorenzo Lu, Tatiana Tommasi
Opublikowane w: IEEE Access, Numer 12, 2025, ISSN 2169-3536
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/ACCESS.2024.3409587

Mask2Anomaly: Mask Transformer for Universal Open-Set Segmentation

Autorzy: Shyam Nandan Rai, Fabio Cermelli, Barbara Caputo, Carlo Masone
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer 46, 2024, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2024.3419055

Modeling Brain Aging With Explainable Triamese ViT: Towards Deeper Insights Into Autism Disorder

Autorzy: Zhaonian Zhang, Vaneet Aggarwal, Plamen Angelov, Richard Jiang
Opublikowane w: IEEE Journal of Biomedical and Health Informatics, Numer 29, 2025, ISSN 2168-2194
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/JBHI.2025.3574366

Learning to mask and permute visual tokens for Vision Transformer pre-training

Autorzy: Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Andrea Pilzer, Rita Cucchiara
Opublikowane w: Computer Vision and Image Understanding, Numer 252, 2025, ISSN 1077-3142
Wydawca: Elsevier BV
DOI: 10.1016/J.CVIU.2025.104294

IDEAL: Interpretable-by-Design ALgorithms for learning from foundation feature spaces

Autorzy: Plamen Angelov, Dmitry Kangin, Ziyang Zhang
Opublikowane w: Neurocomputing, Numer 626, 2025, ISSN 0925-2312
Wydawca: Elsevier BV
DOI: 10.1016/J.NEUCOM.2025.129464

Neuron Activation Pattern and Applications

Autorzy: Z. Jiang, P. Angelov, D. Kangin, …
Opublikowane w: IEEE Transcations on Pattern Analysis and Machine Intelligence, 2024, ISSN 0000-0000
Wydawca: IEEE
DOI: 10.1109/TASE49443.2020.00020

Dispelling the Digital Enchantment: how can we move beyond its destructive influence and reclaim our right to an open future?

Autorzy: Karen Yeung
Opublikowane w: Prometheus, 2023, ISSN 1470-1030
Wydawca: Pluto Journals
DOI: 10.13169/prometheus.39.1.0008

IEEE Transactions on Pattern Analysis and Machine Intelligence

Autorzy: Moritz Böhle, Navdeeppal Singh, Mario Fritz, Bernt Schiele
Opublikowane w: Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024., ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TPAMI.2024.3355155

Delve Into Neural Activations: Toward Understanding Dying Neurons

Autorzy: Ziping Jiang, Yunpeng Wang, Chang-Tsun Li, Plamen Angelov, Richard Jiang
Opublikowane w: IEEE Transactions on Artificial Intelligence, Numer 4, 2024, ISSN 2691-4581
Wydawca: IEEE
DOI: 10.1109/TAI.2022.3180272

Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning

Autorzy: Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Sebastiano Vascon, Werner Zellinger, Bernhard A. Moser, Alina Oprea, Battista Biggio, Marcello Pelillo, Fabio Roli
Opublikowane w: ACM Computing Surveys, Numer 55, 2025, ISSN 0360-0300
Wydawca: Association for Computing Machinery (ACM)
DOI: 10.1145/3585385

From ‘wild west’ to ‘responsible’ AI testing ‘in-the-wild’: lessons from live facial recognition testing by law enforcement authorities in Europe

Autorzy: Karen Yeung, Wenlong Li
Opublikowane w: Data & Policy, Numer 7, 2025, ISSN 2632-3249
Wydawca: Cambridge University Press (CUP)
DOI: 10.1017/DAP.2025.10019

IMAFD: An Interpretable Multi-stage Approach to Flood Detection from time series Multispectral Data

Autorzy: Ziyang Zhang, Plamen Angelov, Dmitry Kangin, Nicolas Longépé
Opublikowane w: Applied Soft Computing, Numer 183, 2025, ISSN 1568-4946
Wydawca: Elsevier BV
DOI: 10.1016/J.ASOC.2025.113582

When Should Algorithms Resign? A Proposal for AI Governance

Autorzy: Umang Bhatt, Holli Sargeant
Opublikowane w: The IEEE Computer Society, ISSN 0018-9162
Wydawca: The IEEE Computer Society
DOI: 10.48550/ARXIV.2402.18326

Building machines that learn and think with people

Autorzy: Katherine M. Collins, Ilia Sucholutsky, Umang Bhatt, Kartik Chandra, Lionel Wong, Mina Lee, Cedegao E. Zhang, Tan Zhi-Xuan, Mark Ho, Vikash Mansinghka, Adrian Weller, Joshua B. Tenenbaum, Thomas L. Griffiths
Opublikowane w: Nature Human Behaviour, Numer 8, 2024, ISSN 2397-3374
Wydawca: Springer Science and Business Media LLC
DOI: 10.1038/S41562-024-01991-9

Fairness Meets Cross-Domain Learning: A Benchmark of Models and Metrics

Autorzy: Leonardo Iurada; Silvia Bucci; Timothy M. Hospedales; Tatiana Tommasi
Opublikowane w: IEEE Access, 2024, ISSN 2169-3536
Wydawca: IEEE
DOI: 10.1109/ACCESS.2024.3383841

Algorithmic loafing and mitigation strategies in Human-AI teams

Autorzy: Isa Inuwa-Dutse, Alice Toniolo, Adrian Weller, Umang Bhatt
Opublikowane w: Computers in Human Behavior: Artificial Humans, Numer 1, 2025, ISSN 2949-8821
Wydawca: Elsevier BV
DOI: 10.1016/J.CHBAH.2023.100024

Investigating over-parameterized randomized graph networks

Autorzy: Giovanni Donghi, Luca Pasa, Luca Oneto, Claudio Gallicchio, Alessio Micheli, Davide Anguita, Alessandro Sperduti, Nicolò Navarin
Opublikowane w: Neurocomputing, Numer 606, 2024, ISSN 0925-2312
Wydawca: Elsevier BV
DOI: 10.1016/J.NEUCOM.2024.128281

Towards Robust Metrics for Concept Representation Evaluation

Autorzy: Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Dmitry Kazhdan, Umang Bhatt, Adrian Weller, Mateja Jamnik
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, Numer 37, 2023, ISSN 2374-3468
Wydawca: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I10.26392

Fair graph representation learning: Empowering NIFTY via Biased Edge Dropout and Fair Attribute Preprocessing

Autorzy: Danilo Franco, Vincenzo Stefano D’Amato, Luca Pasa, Nicolò Navarin, Luca Oneto
Opublikowane w: Neurocomputing, ISSN 1872-8286
Wydawca: Neurocomputing
DOI: 10.1016/J.NEUCOM.2023.126948

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates

Autorzy: Daniele Angioni, Luca Demetrio, Maura Pintor, Luca Oneto, Davide Anguita, Battista Biggio, Fabio Roli
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer 47, 2025, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2025.3573237

Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond

Autorzy: Filippo Galli, Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi, Tommaso Cucinotta
Opublikowane w: Springer Nature Computer Science, 2023, ISSN 2661-8907
Wydawca: Springer Nature
DOI: 10.1007/s42979-023-02292-0

Nebula: Self-Attention for Dynamic Malware Analysis

Autorzy: Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Fabio Roli
Opublikowane w: IEEE Transactions on Information Forensics and Security, Numer 19, 2025, ISSN 1556-6013
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIFS.2024.3409083

ModSec-AdvLearn: Countering Adversarial SQL Injections With Robust Machine Learning

Autorzy: Giuseppe Floris, Christian Scano, Biagio Montaruli, Luca Demetrio, Andrea Valenza, Luca Compagna, Davide Ariu, Luca Piras, Davide Balzarotti, Battista Biggio
Opublikowane w: IEEE Transactions on Information Forensics and Security, Numer 20, 2025, ISSN 1556-6013
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIFS.2025.3583234

Perspectives on incorporating expert feedback into model updates

Autorzy: Valerie Chen, Umang Bhatt, Hoda Heidari, Adrian Weller, Ameet Talwalkar
Opublikowane w: CellPress Open Access - Patterns, ISSN 0000-0000
Wydawca: CellPress Open Access
DOI: 10.1016/J.PATTER.2023.100780

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

Autorzy: Antonio Emanuele Cinà, Jérôme Rony, Maura Pintor, Luca Demetrio, Ambra Demontis, Battista Biggio, Ismail Ben Ayed, Fabio Roli
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, Numer 39, 2025, ISSN 2374-3468
Wydawca: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V39I3.32263

Adversarial Attack Detection via Fuzzy Predictions

Autorzy: Y. Li, P. Angelov, N. Suri
Opublikowane w: IEEE Transactions on Fuzzy Systems, ISSN 1941-0034
Wydawca: IEEE Transactions on Fuzzy Systems
DOI: 10.1109/TFUZZ.2024.3473768

On the robustness of adversarial training against uncertainty attacks

Autorzy: Emanuele Ledda, Giovanni Scodeller, Daniele Angioni, Giorgio Piras, Antonio Emanuele Cinà, Giorgio Fumera, Battista Biggio, Fabio Roli
Opublikowane w: Pattern Recognition, Numer 172, 2025, ISSN 0031-3203
Wydawca: Elsevier BV
DOI: 10.1016/J.PATCOG.2025.112519

Collaborative learning from distributed data with differentially private synthetic data

Autorzy: Lukas Prediger, Joonas Jälkö, Antti Honkela, Samuel Kaski
Opublikowane w: BMC Medical Informatics and Decision Making, Numer 24, 2024, ISSN 1472-6947
Wydawca: Springer Science and Business Media LLC
DOI: 10.1186/S12911-024-02563-7

Hierarchical multimodal transformers for Multipage DocVQA

Autorzy: Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny
Opublikowane w: Pattern Recognition, Numer 144, 2023, ISSN 0031-3203
Wydawca: Elsevier BV
DOI: 10.1016/J.PATCOG.2023.109834

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis

Autorzy: Xiyue Zhang, Xiaoyong Xue, Xiaoning Du, Xiaofei Xie, Yang Liu, Meng Sun
Opublikowane w: IEEE Transactions on Dependable and Secure Computing, Numer 22, 2025, ISSN 1545-5971
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TDSC.2025.3550330

Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation

Autorzy: Luca Barsellotti, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Wydawca: IEEE
DOI: 10.1109/CVPR52733.2024.00354

UnGANable: Defending Against GAN-based Face Manipulation Proceedings Article

Autorzy: Zheng Li; Ning Yu; Ahmed Salem; Michael Backes; Mario Fritz; Yang Zhang
Opublikowane w: USENIX Security Symposium (USENIX Security), 2023
Wydawca: USENIX
DOI: 10.5555/3620237.3620641

Do Invariances in Deep Neural Networks Align with Human Perception?

Autorzy: V. Nanda, A. Majumdar, C. Kolling, J. Dickerson, K. Gummadi, B. Love and A. Weller.
Opublikowane w: Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI), 2023.
Wydawca: AAAI 2023
DOI: 10.1609/AAAI.V37I8.26112

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks

Autorzy: Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev
Opublikowane w: PLDI'23 (Proceedings of the ACM on Programming Languages), 2023, ISSN 2475-1421
Wydawca: """Association for Computing Machinery New York, NY, United States"""
DOI: 10.1145/3591252

Individual Privacy Accounting with Gaussian Differential Privacy

Autorzy: Antti Koskela, Marlon Tobaben, Antti Honkela
Opublikowane w: ICLR 2023, ISSN 2209-15596
Wydawca: ICLR 2023

Client-specific Property Inference against Secure Aggregation in Federated Learning

Autorzy: Raouf Kerkouche, Gergely Ács, Mario Fritz
Opublikowane w: Proceedings of the 22nd Workshop on Privacy in the Electronic Society (WPES), ACM, 2023
Wydawca: WPES
DOI: 10.48550/ARXIV.2303.03908

Certified Robustness of Static Deep Learning-based Malware Detectors against Patch and Append Attacks

Autorzy: Daniel Gibert, Giulio Zizzo, Quan Le
Opublikowane w: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2025
Wydawca: ACM
DOI: 10.1145/3605764.3623914

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

Autorzy: Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz
Opublikowane w: International Conference on Machine Learning (ICML)
Wydawca: International Conference on Machine Learning (ICML)

Hyperbolic Safety-Aware Vision-Language Models

Autorzy: Tobia Poppi;Tejaswi Kasarla;Pascal Mettes;Lorenzo Baraldi;Rita Cucchiara
Opublikowane w: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Wydawca: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

From Attachments to SEO: Click Here to Learn More about Clickbait PDFs!

Autorzy: Giada Stivala; Sahar Abdelnabi; Andrea Mengascini; Mariano Graziano; Mario Fritz; Giancarlo Pellegrino
Opublikowane w: ACSAC '23: Proceedings of the 39th Annual Computer Security Applications Conference
Wydawca: ACSAC 23
DOI: 10.48550/ARXIV.2308.01273

Multitask Learning with No Regret: From Improved Confidence Bounds to Active Learning

Autorzy: Pier Giuseppe Sessa, Pierre Laforgue, Nicolò Cesa-Bianchi, Andreas Krause
Opublikowane w: Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023
Wydawca: Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Autorzy: Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham, Adrian Weller, Zohreh Shams, Mateja Jamnik
Opublikowane w: Neural Information Processing Systems
Wydawca: NeurIPS, 2023
DOI: 10.48550/ARXIV.2309.16928

Is Mamba Capable of In-Context Learning?

Autorzy: Riccardo Grazzi, Julien Niklas Siems, Simon Schrodi, Thomas Brox, Frank Hutter
Opublikowane w: AutoML24
Wydawca: AutoML24
DOI: 10.48550/ARXIV.2402.03170

Harms from Increasingly Agentic Algorithmic Systems

Autorzy: Alan Chan, Rebecca Salganik, Alva Markelius, Chris Pang, Nitarshan Rajkumar, Dmitrii Krasheninnikov, Lauro Langosco, Zhonghao He, Yawen Duan, Micah Carroll, Michelle Lin, Alex Mayhew, Katherine Collins, Maryam Molamohammadi, John Burden, Wanru Zhao, Shalaleh Rismani, Konstantinos Voudouris, Umang Bhatt, Adrian Weller, David Krueger, Tegan Maharaj
Opublikowane w: 2023 ACM Conference on Fairness Accountability and Transparency, 2025
Wydawca: ACM
DOI: 10.1145/3593013.3594033

FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines

Autorzy: Matthew Barker, Emma Kallina, Dhananjay Ashok, Katherine M. Collins, Ashley Casovan, Adrian Weller, Ameet Talwalkar, Valerie Chen, Umang Bhatt
Opublikowane w: ISSN 2307-15475
Wydawca: ACM
DOI: 10.48550/ARXIV.2307.15475

Unmasking Anomalies in Road-Scene Segmentation

Autorzy: Shyam Nandan Rai , Fabio Cermelli, Dario Fontanel, Carlo Masone, Barbara Caputo
Opublikowane w: IEEE Internationa Conference on Computer Vision (ICCV) 2023, 2023
Wydawca: ICCV
DOI: 10.1109/ICCV51070.2023.00373

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

Autorzy: Yugeng Liu, Rui Wen, Xinlei He, Ahmed Salem, Zhikun Zhang, Michael Backes, Emiliano De Cristofaro, Mario Fritz, Yang Zhang
Opublikowane w: USENIX Security Symposium (USENIX Security), 2022
Wydawca: USENIX
DOI: 10.48550/ARXIV.2102.02551

Certified Robust Models with Slack Control and Large Lipschitz Constants Proceedings Article

Autorzy: Max Losch, David Stutz, Bernt Schiele, Mario Fritz
Opublikowane w: DAGM German Conference on Pattern Recognition (GCPR), 2023.
Wydawca: DAGM
DOI: 10.48550/ARXIV.2309.06166

Safety is Essential for Responsible Open-Ended Systems

Autorzy: Ivaxi Sheth, Jan Wehner, Sahar Abdelnabi, Ruta Binkyte, Mario Fritz
Wydawca: ICLR2025
DOI: 10.48550/ARXIV.2502.04512

Improving Fairness via Intrinsic Plasticity in Echo State Networks

Autorzy: Ceni, A. and Bacciu, D. and De Caro, V. and Gallicchio, C. and Oneto, L.
Opublikowane w: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2023, ISBN 978-2-87587-088-9
Wydawca: ESANN
DOI: 10.14428/esann/2023.ES2023-90

Towards interpretable-by-design deep learning algorithms

Autorzy: Plamen Angelov, Dmitry Kangin, Ziyang Zhang
Opublikowane w: UNDER REVIEW, ISSN 2311-11396
Wydawca: N/A
DOI: 10.48550/ARXIV.2311.11396

FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection (CWZS24)

Autorzy: Jialuo Chen, Jingyi Wang, Xiyue Zhang, Youcheng Sun, Marta Kwiatkowska, Jiming Chen, Peng Cheng
Opublikowane w: 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024)., 2024
Wydawca: IEEE
DOI: 10.48550/ARXIV.2409.09130

Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction.

Autorzy: S. Kumar, R. Marjieh, B. Zhang, D. Campbell, M. Hu, U. Bhatt, B. Lake and T. Griffiths.
Opublikowane w: Conference of the Cognitive Science Society (CogSci) 2024
Wydawca: CogSci 2024
DOI: 10.48550/ARXIV.2402.03618

Collaborative Learning via Prediction Consensus

Autorzy: Dongyang Fan, Celestine Mendler-Dünner, Martin Jaggi
Opublikowane w: ISSN 2305-18497
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2305.18497

DRCFS: Doubly Robust Causal Feature Selection

Autorzy: Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer
Opublikowane w: ICML 2023: Fortieth International Conference on Machine Learning, 2023
Wydawca: JMLR.org
DOI: 10.48550/arXiv.2306.07024

Tell Me What You Like and I Know What You Will Share: Topical Interest Influences Behavior Toward News From High and Low Credible Sources

Autorzy: Rebecca Weil; Sahar Abdelnabi; Mario Fritz; Rakibul Hasan
Opublikowane w: European Symposium on Security and Privacy Workshops
Wydawca: EuroS&PW
DOI: 10.1109/EUROSPW61312.2024.00062

Learning Personalized Decision Support Policies

Autorzy: Umang Bhatt, Valerie Chen, Katherine M. Collins, Parameswaran Kamalaruban, Emma Kallina, Adrian Weller, Ameet Talwalkar
Opublikowane w: Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence
Wydawca: AAAI 2025
DOI: 10.48550/ARXIV.2304.06701

LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs

Autorzy: Volker Strobel, Marco Dorigo, Mario Fritz
Opublikowane w: NeurIPS 2024 Workshop on Open-World Agents
Wydawca: NeurIPS 2024
DOI: 10.48550/ARXIV.2410.11387

Data Drift in Android Malware Detection

Autorzy: Luca Minnei, Hicham Eddoubi, Angelo Sotgiu, Maura Pintor, Ambra Demontis, Battista Biggio
Opublikowane w: 2024 International Conference on Machine Learning and Cybernetics (ICMLC), 2025
Wydawca: IEEE
DOI: 10.1109/ICMLC63072.2024.10935015

Adversarial Attacks Against Uncertainty Quantification

Autorzy: Emanuele Ledda, Daniele Angioni, Giorgio Piras, Giorgio Fumera, Battista Biggio, Fabio Roli;
Opublikowane w: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023
Wydawca: ICCV
DOI: 10.48550/ARXIV.2309.10586

LLMs on interactive feature collections with implicit dynamic decision strategy

Autorzy: Juyeon Heo, Vihari Piratla, Kyunghyun Lee, Hyonkeun Joh, Adrian Weller
Opublikowane w: Proceedings of the 31st International Conference on Computational Linguistics
Wydawca: International Conference on Computational Linguistics

The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement

Autorzy: Gabriele Trivigno; Carlo Masone; Barbara Caputo; Torsten Sattler
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Wydawca: IEEE
DOI: 10.48550/ARXIV.2404.10438

Modulating Language Model Experiences through Frictions

Autorzy: Katherine M. Collins, Valerie Chen, Ilia Sucholutsky, Hannah Rose Kirk, Malak Sadek, Holli Sargeant, Ameet Talwalkar, Adrian Weller, Umang Bhatt
Opublikowane w: Neural Information Processing Systems (NeurIPS 2024) Workshop on Behavioral Machine Learning
Wydawca: Neural Information Processing Systems (NeurIPS 2024) Workshop on Behavioral Machine Learning
DOI: 10.48550/ARXIV.2407.12804

ProtoMedX: Towards Explainable Multi-Modal Prototype Learning for Bone Health Classification, I

Autorzy: A Lopez Pellicer, A Mariucci, P Angelov, M Bukhari, JG Kerns
Opublikowane w: ICCV 2025
Wydawca: ICCV 2025

"""Reliability in Semantic Segmentation: Can We Use Synthetic Data? """

Autorzy: Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick Pérez, Matthieu Cord
Opublikowane w: European Conference on Computer Vision (ECCV) 2024, 2024
Wydawca: European Conference on Computer Vision (ECCV) 2024
DOI: 10.48550/ARXIV.2312.09231

Multitask Online Learning: Listen to the Neighborhood Buzz

Autorzy: Juliette Achddou, Nicolò Cesa-Bianchi, Pierre Laforgue
Opublikowane w: Artificial Intelligence and Statistics 2024, ISSN 2310-17385
Wydawca: PMLR Conference Proceedings
DOI: 10.48550/ARXIV.2310.17385

Fuzzy Detectors Against Adversarial Attacks

Autorzy: Y. Li, P. Angelov, N. Suri
Opublikowane w: IEEE Symposium Series on Computational Intelligence, 2023
Wydawca: IEEE Symposium Series on Computational Intelligence

Efficient Certified Training and Robustness Verification of Neural ODEs

Autorzy: Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
Opublikowane w: ICLR, ISSN 2303-05246
Wydawca: ICLR

Generating Scenarios from High-Level Specifications for Object Rearrangement Tasks

Autorzy: Sanne van Waveren, Christian Pek , Iolanda Leite, Jana Tumova, Danica Kragic
Opublikowane w: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), ISSN 2023-0816
Wydawca: IEEE
DOI: 10.1109/IROS55552.2023.10341369

Large Class Separation is Not What You Need for Relational Reasoning-Based OOD Detection

Autorzy: Lorenzo Li Lu, Giulia D’Ascenzi, Francesco Cappio Borlino & Tatiana Tommasi
Opublikowane w: International Conference on Image Analysis and Processing (ICIAP) 2023, ISBN 978-3-031-43153-1
Wydawca: ICIAP
DOI: 10.1007/978-3-031-43153-1_25

Explainable Audio-Visual Representation Learning via Prototypical Contrastive Masked Autoencoder

Autorzy: Y. Li, P. Angelov
Opublikowane w: Advances in neural information processing systems
Wydawca: Advances in neural information processing systems

Towards Biologically Plausible and Private Gene Expression Data Generation Proceedings Article

Autorzy: Dingfan Chen, Marie Oestreich, Tejumade Afonja, Raouf Kerkouche, Matthias Becker, Mario Fritz
Opublikowane w: The 24th Privacy Enhancing Technologies Symposium, 2024.
Wydawca: Privacy Enhancing Technologies Symposium
DOI: 10.48550/ARXIV.2402.04912

EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography

Autorzy: Gabriele Berton, Gabriele Goletto, Gabriele Trivigno, Alex Stoken, Barbara Caputo, Carlo Masone
Opublikowane w: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024
Wydawca: IEEE
DOI: 10.1109/CVPRW63382.2024.00430

Towards More Robust Interpretation via Local Gradient Alignment

Autorzy: S. Joo, S. Jeong, J. Heo, A. Weller and T. Moon.
Opublikowane w: Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence
Wydawca: AAAI 2023
DOI: 10.1609/AAAI.V37I7.25986

Establishing the Price of Privacy in Federated Data Trading

Autorzy: Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi
Opublikowane w: ISSN 2111-15415
Wydawca: PLS
DOI: 10.48550/ARXIV.2111.15415

Federated Document Visual Question Answering: A Pilot Study

Autorzy: Khanh Nguyen, Dimosthenis Karatzas
Opublikowane w: ICDAR 2024
Wydawca: ICDAR 2024
DOI: 10.48550/ARXIV.2405.06636

The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations

Autorzy: Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco, Stefano Leonardi
Opublikowane w: STOC 2024 - 56th ACM Symposium on Theory of Computing, ISSN 2307-09478
Wydawca: ACM Press
DOI: 10.1145/3618260.3649658

Certification of Distributional Individual Fairness

Autorzy: M. Wicker, V. Piratla and A. Weller.
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2023.
Wydawca: NeurIPS 2023
DOI: 10.48550/ARXIV.2311.11911

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

Autorzy: Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza
Opublikowane w: ICLR 2025
Wydawca: ICLR 2025

Poster: Protection against Source Inference Attacks in Federated Learning using Unary Encoding and Shuffling

Autorzy: Andreas Athanasiou, Kangsoo Jung, Catuscia Palamidessi
Opublikowane w: Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2025
Wydawca: ACM
DOI: 10.1145/3658644.3691411

Unsupervised Domain Adaptation within Deep Foundation Latent Spaces

Autorzy: Dmitry Kangin, Plamen Angelov
Opublikowane w: 2nd Workshop on Workshop on Mathematical and Empirical Understanding of Foundation Models
Wydawca: ICLR-2024
DOI: 10.48550/ARXIV.2402.14976FOCUSTOLEARNMORE

Confidential-PROFITT: Confidential PROof of FaIr Training of Trees

Autorzy: Ali Shahin Shamsabadi, Sierra Calanda Wyllie, Nicholas Franzese, Natalie Dullerud, Sébastien Gambs, Nicolas Papernot, Xiao Wang, Adrian Weller
Opublikowane w: The Eleventh International Conference on Learning Representations
Wydawca: Conference on Learning Representations

CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models

Autorzy: Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, Mario Fritz
Opublikowane w: 2nd IEEE Conference on Secure and Trustworthy Machine Learning (SATML), 2024
Wydawca: SATML
DOI: 10.48550/ARXIV.2302.04012

Evaluating the Evaluators: Trust in Adversarial Robustness Tests

Autorzy: Antonio Emanuele Cinà, Maura Pintor, Luca Demetrio, Ambra Demontis, Battista Biggio, Fabio Roli
Wydawca: Ital-IA

Cybersecurity and AI: The PRALab Research Experience

Autorzy: Maura Pintor, Giulia Orrù, Davide Maiorca, Ambra Demontis, Luca Demetrio, Gian Luca Marcialis, Battista Biggio, Fabio Roli
Opublikowane w: 3rd National Conference on Artificial Intelligence, 2023
Wydawca: National Conference on Artificial Intelligence

Machine learning within latent spaces formed by foundation models

Autorzy: B Tomczyk, P Angelov, D Kangin
Opublikowane w: 2024 IEEE 12th International Conference on Intelligent Systems (IS), ISSN 2767-9802
Wydawca: IEEE

Large Language Models Must Be Taught What They Don’t know

Autorzy: Sanyam Kapoor, Nate Gruver, Manley Roberts, Katherine Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Gordon Wilson
Opublikowane w: Conference on Neural Information Processing Systems (NeurIPS 2024).
Wydawca: NeurIPS 2024
DOI: 10.48550/ARXIV.2406.08391

CoTFormer: More Tokens With Attention Make Up For Less Depth

Autorzy: Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi
Opublikowane w: ISSN 2310-10845
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2310.10845

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

Autorzy: Sara Sarto, Manuele Barraco, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Wydawca: CVPR
DOI: 10.48550/ARXIV.2303.12112

Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss,

Autorzy: A Aghasanli, Y Li, P Angelov,
Opublikowane w: Proceedings of the Computer Vision and Pattern Recognition Conference
Wydawca: Computer Vision Foundation

A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets

Autorzy: Ossi Räisä, Antti Honkela
Opublikowane w: AISTATS 2025, 2025
Wydawca: AISTATS 2025
DOI: 10.48550/ARXIV.2402.03985

Adapt to Scarcity: Few-Shot Deepfake Detection via Low-Rank Adaptation

Autorzy: Silvia Cappelletti, Lorenzo Baraldi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Opublikowane w: Lecture Notes in Computer Science, Pattern Recognition, 2024
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-78305-0_8

Expressivity of ReLU-Networks under Convex Relaxations

Autorzy: Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin Vechev
Opublikowane w: ICLR'24, 2023
Wydawca: ICLR
DOI: 10.48550/arXiv.2311.04015

Actsafe: Active exploration with safety constraints for reinforcement learning

Autorzy: As, Yarden and Sukhija, Bhavya and Treven, Lenart and Sferrazza, Carmelo and Coros, Stelian and Krause, Andreas
Opublikowane w: ICLR 2025
Wydawca: ICLR 2025

Adversarial Causal Bayesian Optimization

Autorzy: S. Sussex, P. G. Sessa, A. Makarova, A. Krause
Opublikowane w: International Conference on Learning Representations (ICLR), 2023
Wydawca: ICLR
DOI: 10.48550/arXiv.2307.16625

Pixel-level Certified Explanations via Randomized Smoothing

Autorzy: Alaa Anani, Tobias Lorenz, Mario Frityz, Bernt Schiele
Wydawca: International Conference on Machine Learning (ICML)

Hypothesizing Missing Causal Variables with LLMs

Autorzy: Ivaxi Sheth; Sahar Abdelnabi; Mario Fritz
Opublikowane w: NeurIPS 2024 Workshop on Causality and Large Models (CaLM).
Wydawca: NeurIPS 2024 Workshop on Causality and Large Models (CaLM).
DOI: 10.48550/ARXIV.2409.02604

STEP - Towards Structured Scene-Text Spotting

Autorzy: Sergi Garcia-Bordils, Dimosthenis Karatzas, Marçal Rusiñol
Opublikowane w: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024, ISSN 2309-02356
Wydawca: IEEE Xplore
DOI: 10.1109/WACV57701.2024.00093

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Autorzy: Edoardo Debenedetti; Javier Rando; Daniel Paleka; Fineas Silaghi; Dragos Albastroiu; Niv Cohen; Yuval Lemberg; Reshmi Ghosh; Rui Wen; Ahmed Salem; Giovanni Cherubin;
Opublikowane w: 2024
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2406.07954

Certifiers Make Neural Networks Vulnerable to Availability Attacks

Autorzy: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Opublikowane w: 16th ACM Workshop on Artificial Intelligence and Security (AISec 2023, ISSN 2300-5963
Wydawca: Association for Computing Machinery
DOI: 10.48550/ARXIV.2108.11299

Irreducible Curriculum for Language Model Pretraining

Autorzy: Simin Fan, Martin Jaggi
Opublikowane w: ISSN 2310-15389
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2310.15389

How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations

Autorzy: Siddhartha Gairola, Moritz Böhle, Francesco Locatello, and Bernt Schiele
Opublikowane w: International Conference on Learning Representations
Wydawca: International Conference on Learning Representations

AI Security and Safety: The PRALab Research Experience

Autorzy: Ambra Demontis, Maura Pintor, Luca Demetrio, Angelo Sotgiu, Daniele Angioni, Giorgio Piras, Srishti Gupta, Battista Biggio and Fabio Roli
Opublikowane w: Ital-IA 2023
Wydawca: Ital-IA 2023

Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning

Autorzy: Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Opublikowane w: IEEE CVPR 2024, 2024
Wydawca: IEEE CVPR 2024

Iterative Teaching by Data Hallucination

Autorzy: Z. Qiu, W. Liu, T. Xiao, Z. Liu, U. Bhatt, Y. Luo, A. Weller and B. Schölkopf.
Opublikowane w: International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
Wydawca: AISTATS 2023
DOI: 10.48550/ARXIV.2210.17467

Faster Causal Attention Over Large Sequences Through Sparse Flash Attention

Autorzy: Matteo Pagliardini, Daniele Paliotta, Martin Jaggi, François Fleuret
Opublikowane w: ISSN 2306-01160
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2306.01160

Let's ViCE! Mimicking Human Cognitive Behavior in Image Generation Evaluation

Autorzy: Federico Betti, Jacopo Staiano, Lorenzo Baraldi, Lorenzo Baraldi, Rita Cucchiara, Nicu Sebe
Wydawca: ACM MM
DOI: 10.48550/ARXIV.2307.09416

Certified Training: Small Boxes are All You Need

Autorzy: Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin Vechev
Opublikowane w: ICLR (Spotlight), ISSN 2210-04871
Wydawca: ICLR
DOI: 10.48550/ARXIV.2210.04871

Private Set Generation with Discriminative Information

Autorzy: Dingfan Chen, Raouf Kerkouche, Mario Fritz
Opublikowane w: Neural Information Processing Systems (NeurIPS), 2022
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2211.04446

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

Autorzy: Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang
Opublikowane w: USENIX Security Symposium (USENIX), 2024
Wydawca: USENIX
DOI: 10.5555/3698900.3699117

Robust Self-Supervised Learning for Adversarial Attack Detection

Autorzy: Y. Li, P. Angelov, N. Suri
Opublikowane w: Advances in neural information processing systems
Wydawca: Advances in neural information processing systems

Noise-Aware Differentially Private Variational Inference

Autorzy: Talal Alrawajfeh, Joonas Jälkö, Antti Honkela
Opublikowane w: AISTATS 2025, 2025
Wydawca: AISTATS 2025
DOI: 10.48550/ARXIV.2410.19371

Mitigating Unfair Regression in Machine Learning Model Updates

Autorzy: Irene Buselli, Anna Pallarès López, Eduard Martín Jiménez, Davide Anguita, Fabio Roli, Luca Oneto
Opublikowane w: 2024 International Conference on Machine Learning and Applications (ICMLA), 2025
Wydawca: IEEE
DOI: 10.1109/ICMLA61862.2024.00289

A Simple Recipe for Language-guided Domain Generalized Segmentation

Autorzy: Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, 2024, ISSN 2311-17922
Wydawca: IEEE/CVF
DOI: 10.48550/arXiv.2311.17922

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

Autorzy: Yasser Benigmim, Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Raoul de Charette
Opublikowane w: International Conference on Computer Vision, ICCV 2025
Wydawca: International Conference on Computer Vision, ICCV 2025

When to Trust AI: Advances and Challenges for Certification of Neural Networks

Autorzy: Marta Kwiatkowska, Xiyue Zhang
Opublikowane w: Proceedings of the 18th Conference on Computer Science and Intelligence Systems (FedCSIS 2023), ISSN 2309-11196
Wydawca: Polish Information Processing Society

Geometric Multimodal Contrastive Representation Learning

Autorzy: Petra Poklukar, Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva, Danica Kragic
Wydawca: ICML 22

Learning Safety Constraints for Large Language Models

Autorzy: Xin Chen and Yarden As and Andreas Krause
Opublikowane w: ICML 2025
Wydawca: ICML 2025

Vision-Based Landing Guidance Through Tracking and Orientation Estimation

Autorzy: João P. K. Ferreira, João P. Pinto, Júlia Moura, Yi Li, Cristiano L. Castro, Plamen Angelov
Opublikowane w: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Wydawca: IEEE
DOI: 10.1109/WACV61041.2025.00937

Synthcap: Augmenting transformers with synthetic data for image captioning

Autorzy: Caffagni, D., Barraco, M., Cornia, M., Baraldi, L., Cucchiara, R
Opublikowane w: International Conference on Image Analysis and Processing (ICIAP), 2023
Wydawca: Springer, Cham
DOI: 10.1007/978-3-031-43148-7_10

Efficient Robustness Verification of Neural Ordinary Differential Equations

Autorzy: Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
Opublikowane w: The Symbiosis of Deep Learning and Differential Equations II
Wydawca: The Symbiosis of Deep Learning and Differential Equations II

Puppeteer your robot: Augmented reality leader-follower teleoperation

Autorzy: Jonne Van Haastregt, Michael C Welle, Yuchong Zhang, Danica Kragic
Opublikowane w: 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)
Wydawca: IEEE
DOI: 10.48550/ARXIV.2407.11741

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Autorzy: Egor Zverev, Sahar Abdelnabi, Mario Fritz, Christoph H. Lampert
Opublikowane w: ICLR 2024 Workshop on Secure and Trustworthy Large Language Models
Wydawca: ICLR
DOI: 10.48550/ARXIV.2403.06833

Learning Decision Policies with Instrumental Variables through Double Machine Learning

Autorzy: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Opublikowane w: Forty-first International Conference on Machine Learning
Wydawca: ICML 2024

Stealthy imitation: reward-guided environment-free policy stealing

Autorzy: Zhixiong Zhuang; Maria-Irina Nicolae; Mario Fritz
Opublikowane w: ICML'24: Proceedings of the 41st International Conference on Machine Learning
Wydawca: ICML'24: Proceedings of the 41st International Conference on Machine Learning
DOI: 10.5555/3692070.3694664

The Progression of Disparities within the Criminal Justice System: Differential Enforcement and Risk Assessment Instruments.

Autorzy: Miri Zilka, Riccardo Fogliato, Jiri Hron, Bradley Butcher, Carolyn Ashurst, Adrian Weller
Opublikowane w: ACM Conference on Fairness, Accountability and Transparency (FAccT), 2023.
Wydawca: ACM Digital Library
DOI: 10.1145/3593013.3594099

PØDA: Prompt-driven Zero-shot Domain Adaptation

Autorzy: Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
Opublikowane w: IEEE/CVF International Conference on Computer Vision (ICCV) 2023, 2023
Wydawca: IEEE/CVF
DOI: 10.1109/ICCV51070.2023.01707

TAPS: Connecting Certified and Adversarial Training

Autorzy: Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
Opublikowane w: NeurIPS'23
Wydawca: NeurIPS'23
DOI: 10.48550/ARXIV.2305.04574

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

Autorzy: Riccardo Grazzi; Saverio Salzo; Massimiliano Pontil
Opublikowane w: Journal Of Machine Learning Research, 2024, ISSN 2403-11687
Wydawca: Journal Of Machine Learning Research
DOI: 10.48550/arXiv.2403.11687

Lost in translation: the troubling logics underpinning the embrace of governmental machine-learning based prediction tools for ‘citizen scoring’

Autorzy: Karen Yeung
Opublikowane w: Global Governance by Data
Wydawca: Cambridge University Press
DOI: 10.2139/SSRN.4651480

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation

Autorzy: Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
Opublikowane w: NeurIPS - Datasets and Benchmarks'24
Wydawca: NeurIPS - Datasets and Benchmarks'24
DOI: 10.48550/ARXIV.2309.17234

Optimising for Interpretability: Convolutional Dynamic Alignment Networks

Autorzy: Moritz Böhle, Mario Fritz, Bernt Schiele
Opublikowane w: Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 6, pp. 7625–7638, 2023.
Wydawca: TPAMI
DOI: 10.48550/ARXIV.2109.13004

An Empirical Study of Over-Parameterized Neural Models based on Graph Random Features

Autorzy: Navarin, N. and Pasa, L. and Oneto, L. and Sperduti, A.
Opublikowane w: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), ISBN 978-2-87587-088-9
Wydawca: ESANN
DOI: 10.14428/ESANN/2023.ES2023-145

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Autorzy: Riccardo Grazzi, Julien Siems, Arber Zela, Jörg K.H. Franke, Frank Hutter, Massimiliano Pontil.
Opublikowane w: Proceedings of the International Conference on Learning Representations, 2025
Wydawca: ICLR 2025

Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems Proceedings Article

Autorzy: Sahar Abdelnabi, Mario Fritz
Opublikowane w: USENIX Security Symposium (USENIX Security)}, 2023
Wydawca: USENIX
DOI: 10.48550/ARXIV.2209.03755

Interpretable-through-prototypes deepfake detection for diffusion models

Autorzy: Agil Aghasanli; Dmitry Kangin; Plamen Angelov
Opublikowane w: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), ISSN 2473-9944
Wydawca: IEEE
DOI: 10.1109/ICCVW60793.2023.00053

Tight Differential Privacy Guarantees for the Shuffle Model with k-Randomized Response

Autorzy: Sayan Biswas, Kangsoo Jung, Catuscia Palamidessi
Opublikowane w: ISSN 2205-08858
Wydawca: Foundations & Practice of Security Symposium, FPS 2023.
DOI: 10.1007/978-3-031-57537-2_27

Understanding Certified Training with Interval Bound Propagation

Autorzy: Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
Opublikowane w: ICLR, ISSN 2306-10426
Wydawca: ICLR
DOI: 10.48550/ARXIV.2306.10426

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Autorzy: Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto Del Bimbo, Rita Cucchiara
Opublikowane w: ISSN 2304-00500
Wydawca: UNDER REVIEW ACM TOMM
DOI: 10.48550/ARXIV.2304.00500

Rethinking Self-supervised Learning for Cross-domain Adversarial Sample Recovery

Autorzy: Yi Li, Plamen Angelov, Neeraj Suri
Opublikowane w: ISSN 2161-4393
Wydawca: IJCNN 2024
DOI: 10.1109/IJCNN60899.2024.10650687

Machine Unlearning for Document Classification

Autorzy: Lei Kang, Mohamed Ali Souibgui, Fei Yang, Lluis Gomez, Ernest Valveny, Dimosthenis Karatzas
Opublikowane w: ICDAR 2024
Wydawca: ICDAR 2024
DOI: 10.48550/ARXIV.2404.19031

FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions

Autorzy: Daniel Marta, Simon Holk, Miguel Vasco, Jens Lundell, Timon Homberger, Finn Busch, Olov Andersson, Danica Kragic, Iolanda Leite
Opublikowane w: 2025 International Conference on Robotics and Automation, 2025
Wydawca: IEEE

Cooperative online learning with feedback graphs

Autorzy: Nicolò Cesa-Bianchi, Tommaso Cesari, and Riccardo Della Vecchia
Opublikowane w: Transactions on Machine Learning Research (06/2024), 2024
Wydawca: Transactions on Machine Learning Research (06/2024)

On the informativeness of supervision signals

Autorzy: Ilia Sucholutsky, Ruairidh M. Battleday, Katherine M. Collins, Raja Marjieh, Joshua Peterson, Pulkit Singh, Umang Bhatt, Nori Jacoby, Adrian Weller, Thomas L. Griffiths
Opublikowane w: roceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence,, ISSN 2036-2046
Wydawca: PMLR

Robust Meta-Representation Learning via Global Label Inference and Classification

Autorzy: Ruohan Wang, Isak Falk, Massimiliano Pontil, Carlo Ciliberto
Opublikowane w: 2023
Wydawca: IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI: 10.1109/TPAMI.2023.3328184

Noise-Aware Statistical Inference with Differentially Private Synthetic Data

Autorzy: Ossi Räisä, Joonas Jälkö, Samuel Kaski, Antti Honkela
Opublikowane w: PMLR, ISSN 2205-14485
Wydawca: PMLR

SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models

Autorzy: Hossein Hajipour; Ning Yu; Cristian-Alexandru Staicu; Mario Fritz
Opublikowane w: Findings of the Association for Computational Linguistics: NAACL 2024, 2024.
Wydawca: NAACL
DOI: 10.18653/V1/2024.FINDINGS-NAACL.90

PUDD: Towards Robust Multi-modal Prototype-based Deepfake Detection

Autorzy: A. L. Pellicer, Y. Li, P. Angelov
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)
Wydawca: IEEE

Fast Feature Selection with Fairness Constraints

Autorzy: Francesco Quinzan, Rajiv Khanna, Moshik Hershcovitch, Sarel Cohen, Daniel Waddington, Tobias Friedrich and Michael W. Mahoney
Opublikowane w: 2nd Workshop on Formal Verification of Machine Learning (WFVML 2023), ISSN 2202-13718
Wydawca: PMLR
DOI: 10.48550/ARXIV.2202.13718

Adversarial Robustness Certification for Bayesian Neural Networks

Autorzy: Matthew Wicker, Andrea Patane, Luca Laurenti, Marta Kwiatkowska
Opublikowane w: Lecture Notes in Computer Science
Wydawca: Lecture Notes in Computer Science
DOI: 10.1007/978-3-031-71162-6_1

Use perturbations when learning from explanations

Autorzy: Juyeon Heo, Vihari Piratla, Matthew Wicker, Adrian Weller
Wydawca: NEURIPS

FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations

Autorzy: Hui-Po Wang, Dingfan Chen, Raouf Kerkouche, Mario Fritz
Wydawca: To appear at PETS’24
DOI: 10.48550/ARXIV.2302.01068

Efficient Model Editing with Task-Localized Sparse Fine-tuning

Autorzy: Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Opublikowane w: International Conference on Learning Representations
Wydawca: International Conference on Learning Representations

Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism

Autorzy: Lei Kang, Rubèn Tito, Ernest Valveny, Dimosthenis Karatzas
Opublikowane w: ICDAR 2024
Wydawca: ICDAR 2024
DOI: 10.48550/ARXIV.2404.19024

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

Autorzy: Y. Li, Y. Sun, P. Angelov
Opublikowane w: AAAI Conference on Artificial Intelligence
Wydawca: AAAI Conference on Artificial Intelligence
DOI: 10.48550/ARXIV.2412.08856

Imitation or Innovation? Translating Features of Expressive Motion from Humans to Robots

Autorzy: Benedikte Wallace, Marieke van Otterdijk, Yuchong Zhang, Nona Rajabi, Diego Marin-Bucio, Danica Kragic, Jim Torresen
Opublikowane w: Proceedings of the 12th International Conference on Human-Agent Interaction, 2025
Wydawca: ACM
DOI: 10.1145/3687272.3688302

Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models

Autorzy: Hui-Po Wang; Mario Fritz
Opublikowane w: 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Wydawca: NeurIPS 2024
DOI: 10.48550/ARXIV.2409.17836

Mitigating Robustness Bias: Theoretical Results and Empirical Evidences

Autorzy: Franco, D. and Oneto, L. and Anguita, D.
Opublikowane w: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2023, ISBN 978-2-87587-088-9
Wydawca: ESANN
DOI: 10.14428/esann/2023.ES2023-30

Lecture Notes in Computer Science

Autorzy: Xiyue Zhang, Benjie Wang, Marta Kwiatkowska
Opublikowane w: TACAS 2024, 30th International Conference on Tools and Algorithms for the Construction and Analysis of Systems, 2024, ISSN 0302-9743
Wydawca: Springer
DOI: 10.48550/arXiv.2305.03686

Confidential-DPproof: Confidential Proof of Differentially Private Training

Autorzy: Ali Shahin Shamsabadi, Gefei Tan, Tudor Ioan Cebere, Aurélien Bellet, Hamed Haddadi, Nicolas Papernot, Xiao Wang, Adrian Weller
Opublikowane w: International 12th Conference on Learning Representations
Wydawca: International Conference on Learning Representations

Text-DIAE: A Self-Supervised Degradation Invariant Autoencoder for Text Recognition and Document Enhancement

Autorzy: Mohamed Ali Souibgui, Sanket Biswas, Andres Mafla, Ali Furkan Biten, Alicia Fornés, Yousri Kessentini, Josep Lladós, Lluis Gomez, Dimosthenis Karatzas
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, Numer 37, 2023, ISSN 2374-3468
Wydawca: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V37I2.25328

Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Proceedings Article

Autorzy: Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz
Opublikowane w: 16th ACM Workshop on Artificial Intelligence and Security (AISec), 2023
Wydawca: ACM
DOI: 10.48550/ARXIV.2302.12173

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

Autorzy: Gianni Franchi, Olivier Laurent, Maxence Leguéry, Andrei Bursuc, Andrea Pilzer, Angela Yao
Opublikowane w: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, 2024, ISSN 2312-15297
Wydawca: IEEE/CVF
DOI: 10.48550/arXiv.2312.15297

Human-centered AI Technologies in Human-robot Interaction for Social Settings

Autorzy: Yuchong Zhang, Khaled Kassem, Zhengya Gong, Fan Mo, Yong Ma, Emma Kirjavainen, Jonna Häkkilä
Opublikowane w: Proceedings of the International Conference on Mobile and Ubiquitous Multimedia, 2025
Wydawca: ACM
DOI: 10.1145/3701571.3701610

DoGE: Domain Reweighting with Generalization Estimation

Autorzy: Simin Fan, Matteo Pagliardini, Martin Jaggi
Opublikowane w: ISSN 2310-15393
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2310.15393

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Autorzy: Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu
Opublikowane w: International Conference on Learning Representations (ICLR), 2024
Wydawca: ICLR 2024

Get my drift? Catching LLM Task Drift with Activation Deltas

Autorzy: Sahar Abdelnabi; Aideen Fay; Giovanni Cherubin; Ahmed Salem; Mario Fritz; Andrew Paverd
Opublikowane w: IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , 2025.
Wydawca: SaTML 2025
DOI: 10.48550/ARXIV.2406.00799

Group Meritocratic Fairness in Linear Contextual Bandits

Autorzy: Riccardo Grazzi, Arya Akhavan, John Isak Texas Falk, Leonardo Cella, Massimiliano Pontil
Opublikowane w: NeurIPS 2022
Wydawca: NeurIPS 2022
DOI: 10.48550/ARXIV.2206.03150

ModSec-Learn: Boosting ModSecurity with Machine Learning

Autorzy: Christian Scano, Giuseppe Floris, Biagio Montaruli, Luca Demetrio, Andrea Valenza, Luca Compagna, Davide Ariu, Luca Piras, Davide Balzarotti, Battista Biggio
Opublikowane w: Lecture Notes in Networks and Systems, Distributed Computing and Artificial Intelligence, Special Sessions I, 21st International Conference, 2025
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-76459-2_3

DocVXQA: Context-Aware Visual Explanations for Document Question Answering

Autorzy: Mohamed Ali Souibgui, Changkyu Choi, Andrey Barsky, Kangsoo Jung, Ernest Valveny, Dimosthenis Karatzas
Opublikowane w: International Conference on Machine Learning
Wydawca: International Conference on Machine Learning

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

Autorzy: Khanh Nguyen, Raouf Kerkouche, Mario Fritz, Dimosthenis Karatzas
Opublikowane w: ICLR 2025
Wydawca: ICLR 2025

Privacy-Aware Document Visual Question Answering

Autorzy: Rubèn Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Gangsoo Jung, Joonas Jälkö, Vincent Poulain D'Andecy, Aurelie Joseph, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz and Dimosthenis Karatzas
Opublikowane w: 18th International Conference on Document Analysis and Recognition, ICDAR 2024
Wydawca: ICDAR 2024
DOI: 10.48550/ARXIV.2312.10108

Landmark Attention: Random-Access Infinite Context Length for Transformers

Autorzy: Amirkeivan Mohtashami, Martin Jaggi
Opublikowane w: ISSN 2305-16300
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2305.16300

CoBo: Collaborative Learning via Bilevel Optimization

Autorzy: Diba Hashemi, Lie He, Martin Jaggi
Opublikowane w: NeurIPS 2024
Wydawca: NeurIPS 2024

LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History

Autorzy: Akash Gupta; Ivaxi Sheth; Vyas Raina; Mark Gales; Mario Fritz
Opublikowane w: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Wydawca: Conference on Empirical Methods in Natural Language Processing
DOI: 10.48550/ARXIV.2402.18216

Transient-Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead

Autorzy: Niccolò Cavagnero; Fernando Dos Santos; Marco Ciccone; Giuseppe Averta; Tatiana Tommasi; Paolo Rech
Opublikowane w: 2022 IEEE 28th International Symposium on On-Line Testing and Robust System Design (IOLTS), 2022
Wydawca: IOLTS
DOI: 10.1109/IOLTS56730.2022.9897813

LFPD: Local-Feature-Powered Defense Against Adaptive Backdoor Attacks

Autorzy: Wei Guo, Ambra Demontis, Maura Plntor, Patrick P.K. Chan, Battista Biggio
Opublikowane w: 2024 International Conference on Machine Learning and Cybernetics (ICMLC), 2025
Wydawca: IEEE
DOI: 10.1109/ICMLC63072.2024.10935153

Learning to Generate Training Datasets for Robust Semantic Segmentation

Autorzy: Marwane Hariat, Olivier Laurent, Rémi Kazmierczak, Shihao Zhang, Andrei Bursuc, Angela Yao, Gianni Franchi
Opublikowane w: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024
Wydawca: IEEE/CVF
DOI: 10.48550/ARXIV.2308.02535

Multi-task representation learning with stochastic linear bandits

Autorzy: Leonardo Cella, Karim Lounici, Grégoire Pacreau, Massimiliano Pontil
Opublikowane w: AISTATS 2023
Wydawca: AISTATS 2023

Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning

Autorzy: S, Garcia-Bordils, D. Karatzas, M. Rusiñol
Opublikowane w: Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, ISBN 978-3-031-41731-3
Wydawca: Springer Cham
DOI: 10.1007/978-3-031-41731-3_7

Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis

Autorzy: Cocchi, Federico; Baraldi, Lorenzo; Poppi, Samuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Opublikowane w: Proceedings of the 22nd International Conference on Image Analysis and Processing, ISBN 978-3-031-43152-4
Wydawca: Springer-Verlag
DOI: 10.1007/978-3-031-43153-1_29

CausalGraph2LLM: Evaluating LLMs for Causal Queries

Autorzy: Ivaxi Sheth, Bahare Fatemi, Mario Fritz
Opublikowane w: NAACL'25
Wydawca: NAACL'25

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA

Autorzy: Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aurélie JOSEPH, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kent
Opublikowane w: NEURIPS 2024
Wydawca: NEURIPS 2024
DOI: 10.48550/ARXIV.2411.03730

Robustness Guarantees for Bayesian Neural Networks

Autorzy: Marta Kwiatkowska
Opublikowane w: Proc. 19th International Conference on Quantitative Evaluation of SysTems (QEST 2022), ISSN 1611-3349
Wydawca: Springer
DOI: 10.1007/978-3-031-16336-4

Private and Collaborative Kaplan-Meier Estimators

Autorzy: Shadi Rahimian, Raouf Kerkouche, Ina Kurth, Mario Fritz
Wydawca: ArXiv
DOI: 10.48550/ARXIV.2305.15359

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces

Autorzy: S.S. Ramesh, P. G. Sessa, Y. Hu, A. Krause, I. Bogunovic
Opublikowane w: International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Wydawca: AISTATS
DOI: 10.48550/arXiv.2309.02236

"MargCTGAN: A ""Marginally"" Better CTGAN for the Low Sample Regime"

Autorzy: Tejumade Afonja, Dingfan Chen, Mario Fritz
Wydawca: GCPR’23
DOI: 10.60882/CISPA.25233076

Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention

Autorzy: Matteo Pagliardini ~Matteo_Pagliardini1 , Daniele Paliotta, Martin Jaggi, François Fleuret
Wydawca: NEURIPS 2023

Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation

Autorzy: Ossi Räisä, Joonas Jälkö, Antti Honkela
Wydawca: ICML 2024

On the Efficacy of Differentially Private Few-shot Image Classification

Autorzy: Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella Béguelin, Richard E. Turner, Antti Honkela
Opublikowane w: TMLR 2023, ISSN 2302-01190
Wydawca: TMLR 2023

3DOS: Towards 3D Open Set Learning - Benchmarking and Understanding Semantic Novelty Detection on Point Clouds

Autorzy: Antonio Alliegro, Francesco Cappio Borlino, Tatiana Tommasi
Opublikowane w: Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Datasets and Benchmarks Track, 2022, ISBN 9781713871088
Wydawca: NeurIPS 2022

FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks (LKF24)

Autorzy: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Opublikowane w: The German Conference on Pattern Recognition (GCPR)
Wydawca: The German Conference on Pattern Recognition (GCPR)
DOI: 10.1007/978-3-031-85181-0_5

Hyperparameters in Score-Based Membership Inference Attacks

Autorzy: Gauri Pradhan, Joonas Jälkö, Marlon Tobaben, Antti Honkela
Opublikowane w: SaTML 2025, 2025
Wydawca: SaTML 2025
DOI: 10.48550/ARXIV.2502.06374

The BRAVO Semantic Segmentation Challenge Results in UNCV2024

Autorzy: Tuan-Hung Vu, Eduardo Valle, Andrei Bursuc, Tommie Kerssies, Daan de Geus, Gijs Dubbelman, Long Qian, Bingke Zhu, Yingying Chen, Ming Tang, Jinqiao Wang, Tomáš Vojíř, Jan Šochman, Jiří Matas, Michael Smith, Frank Ferrie, Shamik Basu, Christos Sakaridis, L
Opublikowane w: European Conference on Computer Vision (ECCV) 2024, 2024
Wydawca: European Conference on Computer Vision (ECCV) 2024
DOI: 10.48550/ARXIV.2409.15107

Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots

Autorzy: Gabriele Tiboni, Andrea Protopapa, Tatiana Tommasi, Giuseppe Averta
Opublikowane w: IEEE Internationa Conference on Intelligent Robots and Systems (IROS) 2023, 2023
Wydawca: IROS

1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis

Autorzy: Sewade Ogun, Abraham T. Owodunni, Tobi Olatunji, Eniola Alese, Babatunde Oladimeji, Tejumade Afonja, Kayode Olaleye, Naome A. Etori, Tosin Adewumi
Opublikowane w: Biomedical Research in Artificial Intelligence and Machine Perception
Wydawca: Interspeech 2024
DOI: 10.48550/ARXIV.2406.11727

TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks

Autorzy: Brau, Fabio; Pintor, Maura; Cinà, Antonio Emanuele; Mura, Raffaele; Scionis, Luca; Oneto, Luca; Roli, Fabio; Biggio,Battista
Opublikowane w: The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2025
Wydawca: OpenReview.net

Noise-Aware Differentially Private Regression via Meta-Learning

Autorzy: Ossi Räisä, Stratis Markou, Matthew Ashman, Wessel P Bruinsma, Marlon Tobaben, Antti Honkela, Richard E. Turner
Opublikowane w: NeurIPS 2024
Wydawca: NeurIPS 2024

Less is More? An Ablation Study on AutoAttack for Adversarial Robustness Evaluation

Autorzy: Luca Melis, Luca Scionis, Fabio Brau, Maura Pintor, Battista Biggio
Wydawca: ICML

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

Autorzy: Maura Pintor, Luca Demetrio, Angelo Sotgiu, Ambra Demontis, Nicholas Carlini, Battista Biggio, Fabio Roli
Opublikowane w: Advances in Neural Information Processing Systems 35 (NeurIPS 2022) , 2022
Wydawca: Curran Associates, Inc.
DOI: 10.48550/ARXIV.2106.09947

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

Autorzy: Yaling Shen; Zhixiong Zhuang; Kun Yuang; Maria-Irina Nicolae; Nassir Navab; Nicolas Padoy; Mario Fritz
Wydawca: AAAI 2025
DOI: 10.48550/ARXIV.2502.02438

Robust Explanation Constraints for Neural Networks

Autorzy: Matthew Wicker, Juyeon Heo, Luca Costabello, Adrian Weller
Opublikowane w: International Conference on Learning Representations (ICLR), 2023.
Wydawca: ICLR 2023
DOI: 10.48550/ARXIV.2212.08507

Show, Interpret and Tell: Entity-Aware Contextualised Image Captioning in Wikipedia

Autorzy: K. Nguyen, A. Biten, A. Mafla, L. Gomez, D. Karatzas
Opublikowane w: Proceedings of the AAAI Conference on Artificial Intelligence, ISSN 2159-5399
Wydawca: PKP PS
DOI: 10.1609/AAAI.V37I2.25285

Learning Counterfactually Invariant Predictors

Autorzy: Francesco Quinzan, Cecilia Casolo, Krikamol Muandet, Yucen Luo, Niki Kilbertus
Opublikowane w: 2nd Workshop on Formal Verification of Machine Learning (WFVML 2023), 2023, ISSN 2207-09768
Wydawca: arXiv
DOI: 10.48550/arXiv.2207.09768

On Adversarial Training without Perturbing All Examples Proceedings Article

Autorzy: Max Losch; Mohamed Omran; David Stutz; Mario Fritz; Bernt Schiele
Opublikowane w: The Twelfth International Conference on Learning Representations (ICLR), 2024
Wydawca: OpenReview

Towards Randomized Algorithms and Models that We Can Trust: a Theoretical Perspective

Autorzy: Oneto, L. and Ridella, S. and Anguita, D.
Opublikowane w: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), ISBN 978-2-87587-088-9
Wydawca: ESANN
DOI: 10.14428/ESANN/2023.ES2023-29

Fairness Without Demographic Data: A Survey of Approaches

Autorzy: Carolyn Ashurst, Adrian Weller
Opublikowane w: Equity and Access in Algorithms, Mechanisms, and Optimization, 2025
Wydawca: ACM
DOI: 10.1145/3617694.3623234

Human-in-the-Loop Mixup

Autorzy: Katherine M. Collins, Umang Bhatt, Weiyang Liu, Vihari Piratla, Ilia Sucholutsky, Bradley Love, Adrian Weller
Opublikowane w: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence
Wydawca: PMLR

Residual Deep Gaussian Processes on Manifolds for Geometry-aware Bayesian Optimization on Hyperspheres

Autorzy: Kacper Wyrwal, Viacheslav Borovitskiy
Opublikowane w: ICLR 2025
Wydawca: ICLR 2025

Fair Empirical Risk Minimization Revised

Autorzy: Franco, D. and Oneto, L. and Anguita, D.
Opublikowane w: International Work-Conference on Artificial and Natural Neural Networks (IWANN), 2023, ISBN 978-3-031-43084-8
Wydawca: Springer, Cham
DOI: 10.1007/978-3-031-43085-5_3

Tight Accounting in the Shuffle Model of Differential Privacy

Autorzy: Antti Koskela, Mikko A. Heikkilä ~Mikko_A._Heikkilä1 , Antti Honkela
Wydawca: TMLR 2023

PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics

Autorzy: Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz
Opublikowane w: Findings of the Association for Computational Linguistics: NAACL 2024, 2024.
Wydawca: Findings of the Association for Computational Linguistics: NAACL 2024, 2024.
DOI: 10.48550/ARXIV.2404.04722

EarthLoc: Astronaut Photography Localization by Indexing Earth from Space

Autorzy: Gabriele Berton, Alex Stoken, Barbara Caputo, Carlo Masone
Opublikowane w: CVPR 2024
Wydawca: CVPR 2024
DOI: 10.48550/ARXIV.2403.06758

Will You Participate? Exploring the Potential of Robotics Competitions on Human-centric Topics

Autorzy: Yuchong Zhang, Miguel Vasco, Mårten Björkman, Danica Kragic
Opublikowane w: International Conference on Human-Computer Interaction (HCII) 2024, 2024
Wydawca: Springer
DOI: 10.48550/ARXIV.2403.18616

Edge Implementation of Unsupervised Self-evolving Vision Classifier

Autorzy: P. Angelov, A. Aghasanli
Opublikowane w: IEEE International Conference on Evolving and Adaptive Intelligent Systems 2024, 2024
Wydawca: IEEE International Conference on Evolving and Adaptive Intelligent Systems 2024
DOI: 10.1109/EAIS58494.2024.10570024

Multiplication-Free Transformer Training via Piecewise Affine Operations

Autorzy: Atli Kosson, Martin Jaggi
Opublikowane w: ISSN 2305-17190
Wydawca: NeurIPS
DOI: 10.48550/ARXIV.2305.17190

Human Uncertainty in Concept-Based AI Systems

Autorzy: Katherine Maeve Collins ,Matthew Barker, Mateo Espinosa Zarlenga, Naveen Raman, Umang Bhatt, Mateja Jamnik, Ilia Sucholutsky ,Adrian Weller , Krishnamurthy Dvijotham
Opublikowane w: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023
Wydawca: AIES
DOI: 10.1145/3600211.3604692

Automated Classification of Model Errors on ImageNet

Autorzy: Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
Opublikowane w: NeurIPS'23, 2023
Wydawca: NeurIPS
DOI: 10.48550/arXiv.2401.02430

Media Coverage of Predictive Policing: Bias, Police Engagement, and the Future of Transparency

Autorzy: Harry Camilleri, Carolyn Ashurst, Nithya Jaisankar, Adrian Weller, Miri Zilka
Opublikowane w: Equity and Access in Algorithms, Mechanisms, and Optimization, 2025
Wydawca: ACM
DOI: 10.1145/3617694.3623249

DocILE Benchmark for Document Information Localization and Extraction

Autorzy: Štěpán Šimsa, Milan Šulc, Michal Uřičář, Yash Patel, Ahmed Hamdi, Matěj Kocián, Matyáš Skalický, Jiří Matas, Antoine Doucet, Mickaël Coustaty, Dimosthenis Karatzas
Opublikowane w: Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, 2023, ISBN 978-3-031-41678-1
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-41679-8_9

Trading-off payments and accuracy in online classification with paid stochastic experts

Autorzy: Dirk van der Hoeven, Ciara Pike-Burke, Hao Qiu, Nicolo Cesa-Bianchi
Wydawca: ICML
DOI: 10.5555/3618408.3619857

Self-supervised Representation Learning for Adversarial Attack Detection

Autorzy: Yi Li, Plamen Angelov, Neeraj Suri
Opublikowane w: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73027-6_14

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

Autorzy: Lorenzo Baraldi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Alessandro Nicolosi, Rita Cucchiara
Opublikowane w: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024
Wydawca: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73036-8_12

Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models

Autorzy: Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz
Wydawca: archiv.org

DPVIm: Differentially Private Variational Inference Improved

Autorzy: Joonas Jälkö, Lukas Prediger, Antti Honkela, Samuel Kaski
Opublikowane w: TMLR 9/2023, 2023
Wydawca: TMLR 9/2023

The New Public Analytics as an Emerging Paradigm in Public Sector Administration

Autorzy: Karen Yeung
Wydawca: Tilburg Law Review
DOI: 10.5334/TILR.303

Risk-Averse Certification of Bayesian Neural Networks (ZWG+25)

Autorzy: Xiyue Zhang, Zifan Wang, Yulong Gao, Licio Romao, Alessandro Abate, Marta Kwiatkowska
Opublikowane w: Technical report
Wydawca: Technical report
DOI: 10.48550/ARXIV.2411.19729

Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks (VSLK24)

Autorzy: Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska
Opublikowane w: Technical report
Wydawca: Technical report
DOI: 10.48550/ARXIV.2403.13740

Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models

Autorzy: Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz
Wydawca: api.semanticscholar.org
DOI: 10.48550/ARXIV.2502.21123

The GeometricKernels Package: Heat and Mat\'ern Kernels for Geometric Learning on Manifolds, Meshes, and Graphs

Autorzy: Peter Mostowsky, Vincent Dutordoir, Iskander Azangulov, Noémie Jaquier, Michael John Hutchinson, Aditya Ravuri, Leonel Rozo, Alexander Terenin, Viacheslav Borovitskiy
Wydawca: archiv.org

On Neuron Activation Pattern and Applications

Autorzy: Ziping Jiang, Plamen Angelov, Dmitry Kangin, Zhaonian Zhang, Richard Jiang
Opublikowane w: 2024
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.36227/TECHRXIV.170421894.45150592/V1

FineWeb2: A sparkling update with 1000s of languages

Autorzy: Guilherme Penedo, Hynek Kydlíček, Vinko Sabolčec, Bettina Messmer, Negar Foroutan, Martin Jaggi, Leandro von Werra, Thomas Wolf
Opublikowane w: github open source release
Wydawca: github open source release

Living-off-The-Land Reverse-Shell Detection by Informed Data Augmentation

Autorzy: Trizna, D., Demetrio, L., Biggio, B., & Roli, F.
Opublikowane w: 2024, ISSN 2402-18329
Wydawca: ArXiv
DOI: 10.48550/arXiv.2402.18329

epfLLM Megatron-LLM

Autorzy: AH Cano, M Pagliardini, A Köpf, K Matoba, A Mohtashami, OS Fan, A Marmet, D Bayazit, I Krawczuk, Z Chen, F Salvi, A Bosselut, M Jaggi
Wydawca: GitHub

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs

Autorzy: Thierry Bossy, Julien Vignoud, Tahseen Rabbani, Juan R Troncoso Pastoriza, Martin Jaggi
Opublikowane w: arXiv
Wydawca: arXiv
DOI: 10.48550/ARXIV.2502.05087

On-device collaborative language modeling via a mixture of generalists and specialists

Autorzy: Dongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi
Opublikowane w: arXiv
Wydawca: arXiv
DOI: 10.48550/ARXIV.2409.13931

Evaluating Language Models for Mathematics through Interactions

Autorzy: Katherine M. Collins, Albert Q. Jiang, Simon Frieder, Lionel Wong, Miri Zilka, Umang Bhatt, Thomas Lukasiewicz, Yuhuai Wu, Joshua B. Tenenbaum, William Hart, Timothy Gowers, Wenda Li, Adrian Weller, Mateja Jamnik
Opublikowane w: ISSN 2306-01694
Wydawca: arXiv
DOI: 10.1073/PNAS.2318124121

σ-zero: Gradient-based Optimization of ℓ0-norm Adversarial Examples

Autorzy: Cinà, A.E., Villani, F., Pintor, M., Schönherr, L., Biggio, B., Pelillo, M.,
Opublikowane w: 2024, ISSN 2402-01879
Wydawca: ArXiv
DOI: 10.48550/arXiv.2402.01879

From Managers to Machines: A Reply to Respondents

Autorzy: Karen Yeung
Wydawca: Tilburg Law Review
DOI: 10.5334/TILR.308

Transfer learning from inorganic materials to ivory detection

Autorzy: A. Aghasanli, P. Angelov, D. Kangin, J. Kerns and R. Shepherd
Opublikowane w: Scientific Reports
Wydawca: Scientific Reports

The European Union's AI Act: beyond motherhood and apple pie?

Autorzy: Nathalie A. Smuha, Karen Yeung
Opublikowane w: 2024
Wydawca: Elsevier BV
DOI: 10.2139/SSRN.4874852

STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers

Autorzy: Daqian Shao, Lukas Fesser, Marta Kwiatkowska
Opublikowane w: Technical report, paper under submission, 2023
Wydawca: N/A
DOI: 10.48550/arXiv.2401.05338

Exploring the role of Text in Visual Question Answering on Natural Scenes and Documents

Autorzy: Ruben Perez Tito
Opublikowane w: 2023, ISBN 978-84-124793-5-5
Wydawca: Ediciones Gráficas Rey

Wyszukiwanie danych OpenAIRE...

Rezultaty

Publikacje

Udostępnij tę stronę Udostępnij tę stronę w mediach społecznościowych

Pobierz PDF Pobierz zawartość strony