European Lighthouse on Secure and Safe AI

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

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.

Pubblicazioni

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

Autori: Luca Oneto, Sandro Ridella, Davide Anguita
Pubblicato in: Neurocomputing, Numero 592, 2024, ISSN 0925-2312
Editore: Elsevier BV
DOI: 10.1016/J.NEUCOM.2024.127798

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

Autori: Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio, Giorgio Giacinto, Fabio Roli
Pubblicato in: Pattern Recognition, Numero 168, 2025, ISSN 0031-3203
Editore: Elsevier BV
DOI: 10.1016/J.PATCOG.2025.111788

Informed Machine Learning: Excess risk and generalization

Autori: Luca Oneto, Sandro Ridella, Davide Anguita
Pubblicato in: Neurocomputing, Numero 646, 2025, ISSN 0925-2312
Editore: Elsevier BV
DOI: 10.1016/J.NEUCOM.2025.130521

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

Autori: Luca Demetrio, Battista Biggio
Pubblicato in: SSRN Electronic Journal, 2022, ISSN 1556-5068
Editore: Elsevier BV
DOI: 10.2139/SSRN.4066509

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

Autori: Francesco Cappio Borlino, Lorenzo Lu, Tatiana Tommasi
Pubblicato in: IEEE Access, Numero 12, 2025, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/ACCESS.2024.3409587

Mask2Anomaly: Mask Transformer for Universal Open-Set Segmentation

Autori: Shyam Nandan Rai, Fabio Cermelli, Barbara Caputo, Carlo Masone
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 46, 2024, ISSN 0162-8828
Editore: 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

Autori: Zhaonian Zhang, Vaneet Aggarwal, Plamen Angelov, Richard Jiang
Pubblicato in: IEEE Journal of Biomedical and Health Informatics, Numero 29, 2025, ISSN 2168-2194
Editore: 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

Autori: Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Andrea Pilzer, Rita Cucchiara
Pubblicato in: Computer Vision and Image Understanding, Numero 252, 2025, ISSN 1077-3142
Editore: Elsevier BV
DOI: 10.1016/J.CVIU.2025.104294

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

Autori: Plamen Angelov, Dmitry Kangin, Ziyang Zhang
Pubblicato in: Neurocomputing, Numero 626, 2025, ISSN 0925-2312
Editore: Elsevier BV
DOI: 10.1016/J.NEUCOM.2025.129464

Neuron Activation Pattern and Applications

Autori: Z. Jiang, P. Angelov, D. Kangin, …
Pubblicato in: IEEE Transcations on Pattern Analysis and Machine Intelligence, 2024, ISSN 0000-0000
Editore: 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?

Autori: Karen Yeung
Pubblicato in: Prometheus, 2023, ISSN 1470-1030
Editore: Pluto Journals
DOI: 10.13169/prometheus.39.1.0008

IEEE Transactions on Pattern Analysis and Machine Intelligence

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

Delve Into Neural Activations: Toward Understanding Dying Neurons

Autori: Ziping Jiang, Yunpeng Wang, Chang-Tsun Li, Plamen Angelov, Richard Jiang
Pubblicato in: IEEE Transactions on Artificial Intelligence, Numero 4, 2024, ISSN 2691-4581
Editore: IEEE
DOI: 10.1109/TAI.2022.3180272

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

Autori: Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Sebastiano Vascon, Werner Zellinger, Bernhard A. Moser, Alina Oprea, Battista Biggio, Marcello Pelillo, Fabio Roli
Pubblicato in: ACM Computing Surveys, Numero 55, 2025, ISSN 0360-0300
Editore: 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

Autori: Karen Yeung, Wenlong Li
Pubblicato in: Data & Policy, Numero 7, 2025, ISSN 2632-3249
Editore: Cambridge University Press (CUP)
DOI: 10.1017/DAP.2025.10019

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

Autori: Ziyang Zhang, Plamen Angelov, Dmitry Kangin, Nicolas Longépé
Pubblicato in: Applied Soft Computing, Numero 183, 2025, ISSN 1568-4946
Editore: Elsevier BV
DOI: 10.1016/J.ASOC.2025.113582

When Should Algorithms Resign? A Proposal for AI Governance

Autori: Umang Bhatt, Holli Sargeant
Pubblicato in: The IEEE Computer Society, ISSN 0018-9162
Editore: The IEEE Computer Society
DOI: 10.48550/ARXIV.2402.18326

Building machines that learn and think with people

Autori: 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
Pubblicato in: Nature Human Behaviour, Numero 8, 2024, ISSN 2397-3374
Editore: Springer Science and Business Media LLC
DOI: 10.1038/S41562-024-01991-9

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

Autori: Leonardo Iurada; Silvia Bucci; Timothy M. Hospedales; Tatiana Tommasi
Pubblicato in: IEEE Access, 2024, ISSN 2169-3536
Editore: IEEE
DOI: 10.1109/ACCESS.2024.3383841

Algorithmic loafing and mitigation strategies in Human-AI teams

Autori: Isa Inuwa-Dutse, Alice Toniolo, Adrian Weller, Umang Bhatt
Pubblicato in: Computers in Human Behavior: Artificial Humans, Numero 1, 2025, ISSN 2949-8821
Editore: Elsevier BV
DOI: 10.1016/J.CHBAH.2023.100024

Investigating over-parameterized randomized graph networks

Autori: Giovanni Donghi, Luca Pasa, Luca Oneto, Claudio Gallicchio, Alessio Micheli, Davide Anguita, Alessandro Sperduti, Nicolò Navarin
Pubblicato in: Neurocomputing, Numero 606, 2024, ISSN 0925-2312
Editore: Elsevier BV
DOI: 10.1016/J.NEUCOM.2024.128281

Towards Robust Metrics for Concept Representation Evaluation

Autori: Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Dmitry Kazhdan, Umang Bhatt, Adrian Weller, Mateja Jamnik
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, Numero 37, 2023, ISSN 2374-3468
Editore: 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

Autori: Danilo Franco, Vincenzo Stefano D’Amato, Luca Pasa, Nicolò Navarin, Luca Oneto
Pubblicato in: Neurocomputing, ISSN 1872-8286
Editore: Neurocomputing
DOI: 10.1016/J.NEUCOM.2023.126948

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates

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

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

Autori: Filippo Galli, Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi, Tommaso Cucinotta
Pubblicato in: Springer Nature Computer Science, 2023, ISSN 2661-8907
Editore: Springer Nature
DOI: 10.1007/s42979-023-02292-0

Nebula: Self-Attention for Dynamic Malware Analysis

Autori: Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Fabio Roli
Pubblicato in: IEEE Transactions on Information Forensics and Security, Numero 19, 2025, ISSN 1556-6013
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIFS.2024.3409083

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

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

Perspectives on incorporating expert feedback into model updates

Autori: Valerie Chen, Umang Bhatt, Hoda Heidari, Adrian Weller, Ameet Talwalkar
Pubblicato in: CellPress Open Access - Patterns, ISSN 0000-0000
Editore: CellPress Open Access
DOI: 10.1016/J.PATTER.2023.100780

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

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

Adversarial Attack Detection via Fuzzy Predictions

Autori: Y. Li, P. Angelov, N. Suri
Pubblicato in: IEEE Transactions on Fuzzy Systems, ISSN 1941-0034
Editore: IEEE Transactions on Fuzzy Systems
DOI: 10.1109/TFUZZ.2024.3473768

On the robustness of adversarial training against uncertainty attacks

Autori: Emanuele Ledda, Giovanni Scodeller, Daniele Angioni, Giorgio Piras, Antonio Emanuele Cinà, Giorgio Fumera, Battista Biggio, Fabio Roli
Pubblicato in: Pattern Recognition, Numero 172, 2025, ISSN 0031-3203
Editore: Elsevier BV
DOI: 10.1016/J.PATCOG.2025.112519

Collaborative learning from distributed data with differentially private synthetic data

Autori: Lukas Prediger, Joonas Jälkö, Antti Honkela, Samuel Kaski
Pubblicato in: BMC Medical Informatics and Decision Making, Numero 24, 2024, ISSN 1472-6947
Editore: Springer Science and Business Media LLC
DOI: 10.1186/S12911-024-02563-7

Hierarchical multimodal transformers for Multipage DocVQA

Autori: Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny
Pubblicato in: Pattern Recognition, Numero 144, 2023, ISSN 0031-3203
Editore: Elsevier BV
DOI: 10.1016/J.PATCOG.2023.109834

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis

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

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

Autori: Luca Barsellotti, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editore: IEEE
DOI: 10.1109/CVPR52733.2024.00354

UnGANable: Defending Against GAN-based Face Manipulation Proceedings Article

Autori: Zheng Li; Ning Yu; Ahmed Salem; Michael Backes; Mario Fritz; Yang Zhang
Pubblicato in: USENIX Security Symposium (USENIX Security), 2023
Editore: USENIX
DOI: 10.5555/3620237.3620641

Do Invariances in Deep Neural Networks Align with Human Perception?

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

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks

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

Individual Privacy Accounting with Gaussian Differential Privacy

Autori: Antti Koskela, Marlon Tobaben, Antti Honkela
Pubblicato in: ICLR 2023, ISSN 2209-15596
Editore: ICLR 2023

Client-specific Property Inference against Secure Aggregation in Federated Learning

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

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

Autori: Daniel Gibert, Giulio Zizzo, Quan Le
Pubblicato in: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2025
Editore: ACM
DOI: 10.1145/3605764.3623914

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing

Autori: Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz
Pubblicato in: International Conference on Machine Learning (ICML)
Editore: International Conference on Machine Learning (ICML)

Hyperbolic Safety-Aware Vision-Language Models

Autori: Tobia Poppi;Tejaswi Kasarla;Pascal Mettes;Lorenzo Baraldi;Rita Cucchiara
Pubblicato in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Editore: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

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

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

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

Autori: Pier Giuseppe Sessa, Pierre Laforgue, Nicolò Cesa-Bianchi, Andreas Krause
Pubblicato in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023
Editore: Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Autori: Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham, Adrian Weller, Zohreh Shams, Mateja Jamnik
Pubblicato in: Neural Information Processing Systems
Editore: NeurIPS, 2023
DOI: 10.48550/ARXIV.2309.16928

Is Mamba Capable of In-Context Learning?

Autori: Riccardo Grazzi, Julien Niklas Siems, Simon Schrodi, Thomas Brox, Frank Hutter
Pubblicato in: AutoML24
Editore: AutoML24
DOI: 10.48550/ARXIV.2402.03170

Harms from Increasingly Agentic Algorithmic Systems

Autori: 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
Pubblicato in: 2023 ACM Conference on Fairness Accountability and Transparency, 2025
Editore: ACM
DOI: 10.1145/3593013.3594033

FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines

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

Unmasking Anomalies in Road-Scene Segmentation

Autori: Shyam Nandan Rai , Fabio Cermelli, Dario Fontanel, Carlo Masone, Barbara Caputo
Pubblicato in: IEEE Internationa Conference on Computer Vision (ICCV) 2023, 2023
Editore: ICCV
DOI: 10.1109/ICCV51070.2023.00373

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

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

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

Autori: Max Losch, David Stutz, Bernt Schiele, Mario Fritz
Pubblicato in: DAGM German Conference on Pattern Recognition (GCPR), 2023.
Editore: DAGM
DOI: 10.48550/ARXIV.2309.06166

Safety is Essential for Responsible Open-Ended Systems

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

Improving Fairness via Intrinsic Plasticity in Echo State Networks

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

Towards interpretable-by-design deep learning algorithms

Autori: Plamen Angelov, Dmitry Kangin, Ziyang Zhang
Pubblicato in: UNDER REVIEW, ISSN 2311-11396
Editore: N/A
DOI: 10.48550/ARXIV.2311.11396

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

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

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

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

Collaborative Learning via Prediction Consensus

Autori: Dongyang Fan, Celestine Mendler-Dünner, Martin Jaggi
Pubblicato in: ISSN 2305-18497
Editore: NeurIPS
DOI: 10.48550/ARXIV.2305.18497

DRCFS: Doubly Robust Causal Feature Selection

Autori: Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer
Pubblicato in: ICML 2023: Fortieth International Conference on Machine Learning, 2023
Editore: 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

Autori: Rebecca Weil; Sahar Abdelnabi; Mario Fritz; Rakibul Hasan
Pubblicato in: European Symposium on Security and Privacy Workshops
Editore: EuroS&PW
DOI: 10.1109/EUROSPW61312.2024.00062

Learning Personalized Decision Support Policies

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

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

Autori: Volker Strobel, Marco Dorigo, Mario Fritz
Pubblicato in: NeurIPS 2024 Workshop on Open-World Agents
Editore: NeurIPS 2024
DOI: 10.48550/ARXIV.2410.11387

Data Drift in Android Malware Detection

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

Adversarial Attacks Against Uncertainty Quantification

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

LLMs on interactive feature collections with implicit dynamic decision strategy

Autori: Juyeon Heo, Vihari Piratla, Kyunghyun Lee, Hyonkeun Joh, Adrian Weller
Pubblicato in: Proceedings of the 31st International Conference on Computational Linguistics
Editore: International Conference on Computational Linguistics

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

Autori: Gabriele Trivigno; Carlo Masone; Barbara Caputo; Torsten Sattler
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Editore: IEEE
DOI: 10.48550/ARXIV.2404.10438

Modulating Language Model Experiences through Frictions

Autori: Katherine M. Collins, Valerie Chen, Ilia Sucholutsky, Hannah Rose Kirk, Malak Sadek, Holli Sargeant, Ameet Talwalkar, Adrian Weller, Umang Bhatt
Pubblicato in: Neural Information Processing Systems (NeurIPS 2024) Workshop on Behavioral Machine Learning
Editore: 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

Autori: A Lopez Pellicer, A Mariucci, P Angelov, M Bukhari, JG Kerns
Pubblicato in: ICCV 2025
Editore: ICCV 2025

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

Autori: Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick Pérez, Matthieu Cord
Pubblicato in: European Conference on Computer Vision (ECCV) 2024, 2024
Editore: European Conference on Computer Vision (ECCV) 2024
DOI: 10.48550/ARXIV.2312.09231

Multitask Online Learning: Listen to the Neighborhood Buzz

Autori: Juliette Achddou, Nicolò Cesa-Bianchi, Pierre Laforgue
Pubblicato in: Artificial Intelligence and Statistics 2024, ISSN 2310-17385
Editore: PMLR Conference Proceedings
DOI: 10.48550/ARXIV.2310.17385

Fuzzy Detectors Against Adversarial Attacks

Autori: Y. Li, P. Angelov, N. Suri
Pubblicato in: IEEE Symposium Series on Computational Intelligence, 2023
Editore: IEEE Symposium Series on Computational Intelligence

Efficient Certified Training and Robustness Verification of Neural ODEs

Autori: Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
Pubblicato in: ICLR, ISSN 2303-05246
Editore: ICLR

Generating Scenarios from High-Level Specifications for Object Rearrangement Tasks

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

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

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

Explainable Audio-Visual Representation Learning via Prototypical Contrastive Masked Autoencoder

Autori: Y. Li, P. Angelov
Pubblicato in: Advances in neural information processing systems
Editore: Advances in neural information processing systems

Towards Biologically Plausible and Private Gene Expression Data Generation Proceedings Article

Autori: Dingfan Chen, Marie Oestreich, Tejumade Afonja, Raouf Kerkouche, Matthias Becker, Mario Fritz
Pubblicato in: The 24th Privacy Enhancing Technologies Symposium, 2024.
Editore: Privacy Enhancing Technologies Symposium
DOI: 10.48550/ARXIV.2402.04912

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

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

Towards More Robust Interpretation via Local Gradient Alignment

Autori: S. Joo, S. Jeong, J. Heo, A. Weller and T. Moon.
Pubblicato in: Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence
Editore: AAAI 2023
DOI: 10.1609/AAAI.V37I7.25986

Establishing the Price of Privacy in Federated Data Trading

Autori: Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi
Pubblicato in: ISSN 2111-15415
Editore: PLS
DOI: 10.48550/ARXIV.2111.15415

Federated Document Visual Question Answering: A Pilot Study

Autori: Khanh Nguyen, Dimosthenis Karatzas
Pubblicato in: ICDAR 2024
Editore: ICDAR 2024
DOI: 10.48550/ARXIV.2405.06636

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

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

Certification of Distributional Individual Fairness

Autori: M. Wicker, V. Piratla and A. Weller.
Pubblicato in: Neural Information Processing Systems (NeurIPS), 2023.
Editore: NeurIPS 2023
DOI: 10.48550/ARXIV.2311.11911

MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

Autori: Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza
Pubblicato in: ICLR 2025
Editore: ICLR 2025

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

Autori: Andreas Athanasiou, Kangsoo Jung, Catuscia Palamidessi
Pubblicato in: Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2025
Editore: ACM
DOI: 10.1145/3658644.3691411

Unsupervised Domain Adaptation within Deep Foundation Latent Spaces

Autori: Dmitry Kangin, Plamen Angelov
Pubblicato in: 2nd Workshop on Workshop on Mathematical and Empirical Understanding of Foundation Models
Editore: ICLR-2024
DOI: 10.48550/ARXIV.2402.14976FOCUSTOLEARNMORE

Confidential-PROFITT: Confidential PROof of FaIr Training of Trees

Autori: Ali Shahin Shamsabadi, Sierra Calanda Wyllie, Nicholas Franzese, Natalie Dullerud, Sébastien Gambs, Nicolas Papernot, Xiao Wang, Adrian Weller
Pubblicato in: The Eleventh International Conference on Learning Representations
Editore: Conference on Learning Representations

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

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

Evaluating the Evaluators: Trust in Adversarial Robustness Tests

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

Cybersecurity and AI: The PRALab Research Experience

Autori: Maura Pintor, Giulia Orrù, Davide Maiorca, Ambra Demontis, Luca Demetrio, Gian Luca Marcialis, Battista Biggio, Fabio Roli
Pubblicato in: 3rd National Conference on Artificial Intelligence, 2023
Editore: National Conference on Artificial Intelligence

Machine learning within latent spaces formed by foundation models

Autori: B Tomczyk, P Angelov, D Kangin
Pubblicato in: 2024 IEEE 12th International Conference on Intelligent Systems (IS), ISSN 2767-9802
Editore: IEEE

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

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

CoTFormer: More Tokens With Attention Make Up For Less Depth

Autori: Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi
Pubblicato in: ISSN 2310-10845
Editore: NeurIPS
DOI: 10.48550/ARXIV.2310.10845

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

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

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

Autori: A Aghasanli, Y Li, P Angelov,
Pubblicato in: Proceedings of the Computer Vision and Pattern Recognition Conference
Editore: Computer Vision Foundation

A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets

Autori: Ossi Räisä, Antti Honkela
Pubblicato in: AISTATS 2025, 2025
Editore: AISTATS 2025
DOI: 10.48550/ARXIV.2402.03985

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

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

Expressivity of ReLU-Networks under Convex Relaxations

Autori: Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin Vechev
Pubblicato in: ICLR'24, 2023
Editore: ICLR
DOI: 10.48550/arXiv.2311.04015

Actsafe: Active exploration with safety constraints for reinforcement learning

Autori: As, Yarden and Sukhija, Bhavya and Treven, Lenart and Sferrazza, Carmelo and Coros, Stelian and Krause, Andreas
Pubblicato in: ICLR 2025
Editore: ICLR 2025

Adversarial Causal Bayesian Optimization

Autori: S. Sussex, P. G. Sessa, A. Makarova, A. Krause
Pubblicato in: International Conference on Learning Representations (ICLR), 2023
Editore: ICLR
DOI: 10.48550/arXiv.2307.16625

Pixel-level Certified Explanations via Randomized Smoothing

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

Hypothesizing Missing Causal Variables with LLMs

Autori: Ivaxi Sheth; Sahar Abdelnabi; Mario Fritz
Pubblicato in: NeurIPS 2024 Workshop on Causality and Large Models (CaLM).
Editore: NeurIPS 2024 Workshop on Causality and Large Models (CaLM).
DOI: 10.48550/ARXIV.2409.02604

STEP - Towards Structured Scene-Text Spotting

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

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

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

Certifiers Make Neural Networks Vulnerable to Availability Attacks

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

Irreducible Curriculum for Language Model Pretraining

Autori: Simin Fan, Martin Jaggi
Pubblicato in: ISSN 2310-15389
Editore: NeurIPS
DOI: 10.48550/ARXIV.2310.15389

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

Autori: Siddhartha Gairola, Moritz Böhle, Francesco Locatello, and Bernt Schiele
Pubblicato in: International Conference on Learning Representations
Editore: International Conference on Learning Representations

AI Security and Safety: The PRALab Research Experience

Autori: Ambra Demontis, Maura Pintor, Luca Demetrio, Angelo Sotgiu, Daniele Angioni, Giorgio Piras, Srishti Gupta, Battista Biggio and Fabio Roli
Pubblicato in: Ital-IA 2023
Editore: Ital-IA 2023

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

Autori: Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Pubblicato in: IEEE CVPR 2024, 2024
Editore: IEEE CVPR 2024

Iterative Teaching by Data Hallucination

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

Faster Causal Attention Over Large Sequences Through Sparse Flash Attention

Autori: Matteo Pagliardini, Daniele Paliotta, Martin Jaggi, François Fleuret
Pubblicato in: ISSN 2306-01160
Editore: NeurIPS
DOI: 10.48550/ARXIV.2306.01160

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

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

Certified Training: Small Boxes are All You Need

Autori: Mark Niklas Müller, Franziska Eckert, Marc Fischer, Martin Vechev
Pubblicato in: ICLR (Spotlight), ISSN 2210-04871
Editore: ICLR
DOI: 10.48550/ARXIV.2210.04871

Private Set Generation with Discriminative Information

Autori: Dingfan Chen, Raouf Kerkouche, Mario Fritz
Pubblicato in: Neural Information Processing Systems (NeurIPS), 2022
Editore: NeurIPS
DOI: 10.48550/ARXIV.2211.04446

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

Autori: Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang
Pubblicato in: USENIX Security Symposium (USENIX), 2024
Editore: USENIX
DOI: 10.5555/3698900.3699117

Robust Self-Supervised Learning for Adversarial Attack Detection

Autori: Y. Li, P. Angelov, N. Suri
Pubblicato in: Advances in neural information processing systems
Editore: Advances in neural information processing systems

Noise-Aware Differentially Private Variational Inference

Autori: Talal Alrawajfeh, Joonas Jälkö, Antti Honkela
Pubblicato in: AISTATS 2025, 2025
Editore: AISTATS 2025
DOI: 10.48550/ARXIV.2410.19371

Mitigating Unfair Regression in Machine Learning Model Updates

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

A Simple Recipe for Language-guided Domain Generalized Segmentation

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

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

Autori: Yasser Benigmim, Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Raoul de Charette
Pubblicato in: International Conference on Computer Vision, ICCV 2025
Editore: International Conference on Computer Vision, ICCV 2025

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

Autori: Marta Kwiatkowska, Xiyue Zhang
Pubblicato in: Proceedings of the 18th Conference on Computer Science and Intelligence Systems (FedCSIS 2023), ISSN 2309-11196
Editore: Polish Information Processing Society

Geometric Multimodal Contrastive Representation Learning

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

Learning Safety Constraints for Large Language Models

Autori: Xin Chen and Yarden As and Andreas Krause
Pubblicato in: ICML 2025
Editore: ICML 2025

Vision-Based Landing Guidance Through Tracking and Orientation Estimation

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

Synthcap: Augmenting transformers with synthetic data for image captioning

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

Efficient Robustness Verification of Neural Ordinary Differential Equations

Autori: Mustafa Zeqiri, Mark Niklas Müller, Marc Fischer, Martin Vechev
Pubblicato in: The Symbiosis of Deep Learning and Differential Equations II
Editore: The Symbiosis of Deep Learning and Differential Equations II

Puppeteer your robot: Augmented reality leader-follower teleoperation

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

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

Autori: Egor Zverev, Sahar Abdelnabi, Mario Fritz, Christoph H. Lampert
Pubblicato in: ICLR 2024 Workshop on Secure and Trustworthy Large Language Models
Editore: ICLR
DOI: 10.48550/ARXIV.2403.06833

Learning Decision Policies with Instrumental Variables through Double Machine Learning

Autori: Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
Pubblicato in: Forty-first International Conference on Machine Learning
Editore: ICML 2024

Stealthy imitation: reward-guided environment-free policy stealing

Autori: Zhixiong Zhuang; Maria-Irina Nicolae; Mario Fritz
Pubblicato in: ICML'24: Proceedings of the 41st International Conference on Machine Learning
Editore: 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.

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

PØDA: Prompt-driven Zero-shot Domain Adaptation

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

TAPS: Connecting Certified and Adversarial Training

Autori: Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
Pubblicato in: NeurIPS'23
Editore: NeurIPS'23
DOI: 10.48550/ARXIV.2305.04574

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

Autori: Riccardo Grazzi; Saverio Salzo; Massimiliano Pontil
Pubblicato in: Journal Of Machine Learning Research, 2024, ISSN 2403-11687
Editore: 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’

Autori: Karen Yeung
Pubblicato in: Global Governance by Data
Editore: Cambridge University Press
DOI: 10.2139/SSRN.4651480

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

Autori: Sahar Abdelnabi, Amr Gomaa, Sarath Sivaprasad, Lea Schönherr, Mario Fritz
Pubblicato in: NeurIPS - Datasets and Benchmarks'24
Editore: NeurIPS - Datasets and Benchmarks'24
DOI: 10.48550/ARXIV.2309.17234

Optimising for Interpretability: Convolutional Dynamic Alignment Networks

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

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

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

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Autori: Riccardo Grazzi, Julien Siems, Arber Zela, Jörg K.H. Franke, Frank Hutter, Massimiliano Pontil.
Pubblicato in: Proceedings of the International Conference on Learning Representations, 2025
Editore: ICLR 2025

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

Autori: Sahar Abdelnabi, Mario Fritz
Pubblicato in: USENIX Security Symposium (USENIX Security)}, 2023
Editore: USENIX
DOI: 10.48550/ARXIV.2209.03755

Interpretable-through-prototypes deepfake detection for diffusion models

Autori: Agil Aghasanli; Dmitry Kangin; Plamen Angelov
Pubblicato in: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), ISSN 2473-9944
Editore: IEEE
DOI: 10.1109/ICCVW60793.2023.00053

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

Autori: Sayan Biswas, Kangsoo Jung, Catuscia Palamidessi
Pubblicato in: ISSN 2205-08858
Editore: Foundations & Practice of Security Symposium, FPS 2023.
DOI: 10.1007/978-3-031-57537-2_27

Understanding Certified Training with Interval Bound Propagation

Autori: Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
Pubblicato in: ICLR, ISSN 2306-10426
Editore: ICLR
DOI: 10.48550/ARXIV.2306.10426

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Autori: Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto Del Bimbo, Rita Cucchiara
Pubblicato in: ISSN 2304-00500
Editore: UNDER REVIEW ACM TOMM
DOI: 10.48550/ARXIV.2304.00500

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

Autori: Yi Li, Plamen Angelov, Neeraj Suri
Pubblicato in: ISSN 2161-4393
Editore: IJCNN 2024
DOI: 10.1109/IJCNN60899.2024.10650687

Machine Unlearning for Document Classification

Autori: Lei Kang, Mohamed Ali Souibgui, Fei Yang, Lluis Gomez, Ernest Valveny, Dimosthenis Karatzas
Pubblicato in: ICDAR 2024
Editore: ICDAR 2024
DOI: 10.48550/ARXIV.2404.19031

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

Autori: Daniel Marta, Simon Holk, Miguel Vasco, Jens Lundell, Timon Homberger, Finn Busch, Olov Andersson, Danica Kragic, Iolanda Leite
Pubblicato in: 2025 International Conference on Robotics and Automation, 2025
Editore: IEEE

Cooperative online learning with feedback graphs

Autori: Nicolò Cesa-Bianchi, Tommaso Cesari, and Riccardo Della Vecchia
Pubblicato in: Transactions on Machine Learning Research (06/2024), 2024
Editore: Transactions on Machine Learning Research (06/2024)

On the informativeness of supervision signals

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

Robust Meta-Representation Learning via Global Label Inference and Classification

Autori: Ruohan Wang, Isak Falk, Massimiliano Pontil, Carlo Ciliberto
Pubblicato in: 2023
Editore: IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI: 10.1109/TPAMI.2023.3328184

Noise-Aware Statistical Inference with Differentially Private Synthetic Data

Autori: Ossi Räisä, Joonas Jälkö, Samuel Kaski, Antti Honkela
Pubblicato in: PMLR, ISSN 2205-14485
Editore: PMLR

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

Autori: Hossein Hajipour; Ning Yu; Cristian-Alexandru Staicu; Mario Fritz
Pubblicato in: Findings of the Association for Computational Linguistics: NAACL 2024, 2024.
Editore: NAACL
DOI: 10.18653/V1/2024.FINDINGS-NAACL.90

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

Autori: A. L. Pellicer, Y. Li, P. Angelov
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)
Editore: IEEE

Fast Feature Selection with Fairness Constraints

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

Adversarial Robustness Certification for Bayesian Neural Networks

Autori: Matthew Wicker, Andrea Patane, Luca Laurenti, Marta Kwiatkowska
Pubblicato in: Lecture Notes in Computer Science
Editore: Lecture Notes in Computer Science
DOI: 10.1007/978-3-031-71162-6_1

Use perturbations when learning from explanations

Autori: Juyeon Heo, Vihari Piratla, Matthew Wicker, Adrian Weller
Editore: NEURIPS

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

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

Efficient Model Editing with Task-Localized Sparse Fine-tuning

Autori: Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Pubblicato in: International Conference on Learning Representations
Editore: International Conference on Learning Representations

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

Autori: Lei Kang, Rubèn Tito, Ernest Valveny, Dimosthenis Karatzas
Pubblicato in: ICDAR 2024
Editore: ICDAR 2024
DOI: 10.48550/ARXIV.2404.19024

Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement

Autori: Y. Li, Y. Sun, P. Angelov
Pubblicato in: AAAI Conference on Artificial Intelligence
Editore: AAAI Conference on Artificial Intelligence
DOI: 10.48550/ARXIV.2412.08856

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

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

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

Autori: Hui-Po Wang; Mario Fritz
Pubblicato in: 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Editore: NeurIPS 2024
DOI: 10.48550/ARXIV.2409.17836

Mitigating Robustness Bias: Theoretical Results and Empirical Evidences

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

Lecture Notes in Computer Science

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

Confidential-DPproof: Confidential Proof of Differentially Private Training

Autori: Ali Shahin Shamsabadi, Gefei Tan, Tudor Ioan Cebere, Aurélien Bellet, Hamed Haddadi, Nicolas Papernot, Xiao Wang, Adrian Weller
Pubblicato in: International 12th Conference on Learning Representations
Editore: International Conference on Learning Representations

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

Autori: Mohamed Ali Souibgui, Sanket Biswas, Andres Mafla, Ali Furkan Biten, Alicia Fornés, Yousri Kessentini, Josep Lladós, Lluis Gomez, Dimosthenis Karatzas
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, Numero 37, 2023, ISSN 2374-3468
Editore: 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

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

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

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

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

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

DoGE: Domain Reweighting with Generalization Estimation

Autori: Simin Fan, Matteo Pagliardini, Martin Jaggi
Pubblicato in: ISSN 2310-15393
Editore: NeurIPS
DOI: 10.48550/ARXIV.2310.15393

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Autori: Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu
Pubblicato in: International Conference on Learning Representations (ICLR), 2024
Editore: ICLR 2024

Get my drift? Catching LLM Task Drift with Activation Deltas

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

Group Meritocratic Fairness in Linear Contextual Bandits

Autori: Riccardo Grazzi, Arya Akhavan, John Isak Texas Falk, Leonardo Cella, Massimiliano Pontil
Pubblicato in: NeurIPS 2022
Editore: NeurIPS 2022
DOI: 10.48550/ARXIV.2206.03150

ModSec-Learn: Boosting ModSecurity with Machine Learning

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

DocVXQA: Context-Aware Visual Explanations for Document Question Answering

Autori: Mohamed Ali Souibgui, Changkyu Choi, Andrey Barsky, Kangsoo Jung, Ernest Valveny, Dimosthenis Karatzas
Pubblicato in: International Conference on Machine Learning
Editore: International Conference on Machine Learning

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

Autori: Khanh Nguyen, Raouf Kerkouche, Mario Fritz, Dimosthenis Karatzas
Pubblicato in: ICLR 2025
Editore: ICLR 2025

Privacy-Aware Document Visual Question Answering

Autori: 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
Pubblicato in: 18th International Conference on Document Analysis and Recognition, ICDAR 2024
Editore: ICDAR 2024
DOI: 10.48550/ARXIV.2312.10108

Landmark Attention: Random-Access Infinite Context Length for Transformers

Autori: Amirkeivan Mohtashami, Martin Jaggi
Pubblicato in: ISSN 2305-16300
Editore: NeurIPS
DOI: 10.48550/ARXIV.2305.16300

CoBo: Collaborative Learning via Bilevel Optimization

Autori: Diba Hashemi, Lie He, Martin Jaggi
Pubblicato in: NeurIPS 2024
Editore: NeurIPS 2024

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

Autori: Akash Gupta; Ivaxi Sheth; Vyas Raina; Mark Gales; Mario Fritz
Pubblicato in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Editore: 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

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

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

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

Learning to Generate Training Datasets for Robust Semantic Segmentation

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

Multi-task representation learning with stochastic linear bandits

Autori: Leonardo Cella, Karim Lounici, Grégoire Pacreau, Massimiliano Pontil
Pubblicato in: AISTATS 2023
Editore: AISTATS 2023

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

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

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

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

CausalGraph2LLM: Evaluating LLMs for Causal Queries

Autori: Ivaxi Sheth, Bahare Fatemi, Mario Fritz
Pubblicato in: NAACL'25
Editore: NAACL'25

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA

Autori: 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
Pubblicato in: NEURIPS 2024
Editore: NEURIPS 2024
DOI: 10.48550/ARXIV.2411.03730

Robustness Guarantees for Bayesian Neural Networks

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

Private and Collaborative Kaplan-Meier Estimators

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

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces

Autori: S.S. Ramesh, P. G. Sessa, Y. Hu, A. Krause, I. Bogunovic
Pubblicato in: International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Editore: AISTATS
DOI: 10.48550/arXiv.2309.02236

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

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

Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention

Autori: Matteo Pagliardini ~Matteo_Pagliardini1 , Daniele Paliotta, Martin Jaggi, François Fleuret
Editore: NEURIPS 2023

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

Autori: Ossi Räisä, Joonas Jälkö, Antti Honkela
Editore: ICML 2024

On the Efficacy of Differentially Private Few-shot Image Classification

Autori: Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella Béguelin, Richard E. Turner, Antti Honkela
Pubblicato in: TMLR 2023, ISSN 2302-01190
Editore: TMLR 2023

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

Autori: Antonio Alliegro, Francesco Cappio Borlino, Tatiana Tommasi
Pubblicato in: Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Datasets and Benchmarks Track, 2022, ISBN 9781713871088
Editore: NeurIPS 2022

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

Autori: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Pubblicato in: The German Conference on Pattern Recognition (GCPR)
Editore: The German Conference on Pattern Recognition (GCPR)
DOI: 10.1007/978-3-031-85181-0_5

Hyperparameters in Score-Based Membership Inference Attacks

Autori: Gauri Pradhan, Joonas Jälkö, Marlon Tobaben, Antti Honkela
Pubblicato in: SaTML 2025, 2025
Editore: SaTML 2025
DOI: 10.48550/ARXIV.2502.06374

The BRAVO Semantic Segmentation Challenge Results in UNCV2024

Autori: 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
Pubblicato in: European Conference on Computer Vision (ECCV) 2024, 2024
Editore: 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

Autori: Gabriele Tiboni, Andrea Protopapa, Tatiana Tommasi, Giuseppe Averta
Pubblicato in: IEEE Internationa Conference on Intelligent Robots and Systems (IROS) 2023, 2023
Editore: IROS

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

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

TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks

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

Noise-Aware Differentially Private Regression via Meta-Learning

Autori: Ossi Räisä, Stratis Markou, Matthew Ashman, Wessel P Bruinsma, Marlon Tobaben, Antti Honkela, Richard E. Turner
Pubblicato in: NeurIPS 2024
Editore: NeurIPS 2024

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

Autori: Luca Melis, Luca Scionis, Fabio Brau, Maura Pintor, Battista Biggio
Editore: ICML

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

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

Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment

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

Robust Explanation Constraints for Neural Networks

Autori: Matthew Wicker, Juyeon Heo, Luca Costabello, Adrian Weller
Pubblicato in: International Conference on Learning Representations (ICLR), 2023.
Editore: ICLR 2023
DOI: 10.48550/ARXIV.2212.08507

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

Autori: K. Nguyen, A. Biten, A. Mafla, L. Gomez, D. Karatzas
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, ISSN 2159-5399
Editore: PKP PS
DOI: 10.1609/AAAI.V37I2.25285

Learning Counterfactually Invariant Predictors

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

On Adversarial Training without Perturbing All Examples Proceedings Article

Autori: Max Losch; Mohamed Omran; David Stutz; Mario Fritz; Bernt Schiele
Pubblicato in: The Twelfth International Conference on Learning Representations (ICLR), 2024
Editore: OpenReview

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

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

Fairness Without Demographic Data: A Survey of Approaches

Autori: Carolyn Ashurst, Adrian Weller
Pubblicato in: Equity and Access in Algorithms, Mechanisms, and Optimization, 2025
Editore: ACM
DOI: 10.1145/3617694.3623234

Human-in-the-Loop Mixup

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

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

Autori: Kacper Wyrwal, Viacheslav Borovitskiy
Pubblicato in: ICLR 2025
Editore: ICLR 2025

Fair Empirical Risk Minimization Revised

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

Tight Accounting in the Shuffle Model of Differential Privacy

Autori: Antti Koskela, Mikko A. Heikkilä ~Mikko_A._Heikkilä1 , Antti Honkela
Editore: TMLR 2023

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

Autori: Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz
Pubblicato in: Findings of the Association for Computational Linguistics: NAACL 2024, 2024.
Editore: 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

Autori: Gabriele Berton, Alex Stoken, Barbara Caputo, Carlo Masone
Pubblicato in: CVPR 2024
Editore: CVPR 2024
DOI: 10.48550/ARXIV.2403.06758

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

Autori: Yuchong Zhang, Miguel Vasco, Mårten Björkman, Danica Kragic
Pubblicato in: International Conference on Human-Computer Interaction (HCII) 2024, 2024
Editore: Springer
DOI: 10.48550/ARXIV.2403.18616

Edge Implementation of Unsupervised Self-evolving Vision Classifier

Autori: P. Angelov, A. Aghasanli
Pubblicato in: IEEE International Conference on Evolving and Adaptive Intelligent Systems 2024, 2024
Editore: IEEE International Conference on Evolving and Adaptive Intelligent Systems 2024
DOI: 10.1109/EAIS58494.2024.10570024

Multiplication-Free Transformer Training via Piecewise Affine Operations

Autori: Atli Kosson, Martin Jaggi
Pubblicato in: ISSN 2305-17190
Editore: NeurIPS
DOI: 10.48550/ARXIV.2305.17190

Human Uncertainty in Concept-Based AI Systems

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

Automated Classification of Model Errors on ImageNet

Autori: Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
Pubblicato in: NeurIPS'23, 2023
Editore: NeurIPS
DOI: 10.48550/arXiv.2401.02430

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

Autori: Harry Camilleri, Carolyn Ashurst, Nithya Jaisankar, Adrian Weller, Miri Zilka
Pubblicato in: Equity and Access in Algorithms, Mechanisms, and Optimization, 2025
Editore: ACM
DOI: 10.1145/3617694.3623249

DocILE Benchmark for Document Information Localization and Extraction

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

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

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

Self-supervised Representation Learning for Adversarial Attack Detection

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

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

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

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

Autori: Jan Wehner, Sahar Abdelnabi, Daniel Tan, David Krueger, Mario Fritz
Editore: archiv.org

DPVIm: Differentially Private Variational Inference Improved

Autori: Joonas Jälkö, Lukas Prediger, Antti Honkela, Samuel Kaski
Pubblicato in: TMLR 9/2023, 2023
Editore: TMLR 9/2023

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

Autori: Karen Yeung
Editore: Tilburg Law Review
DOI: 10.5334/TILR.303

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

Autori: Xiyue Zhang, Zifan Wang, Yulong Gao, Licio Romao, Alessandro Abate, Marta Kwiatkowska
Pubblicato in: Technical report
Editore: Technical report
DOI: 10.48550/ARXIV.2411.19729

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

Autori: Jon Vadillo, Roberto Santana, Jose A. Lozano, Marta Kwiatkowska
Pubblicato in: Technical report
Editore: Technical report
DOI: 10.48550/ARXIV.2403.13740

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

Autori: Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz
Editore: 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

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

On Neuron Activation Pattern and Applications

Autori: Ziping Jiang, Plamen Angelov, Dmitry Kangin, Zhaonian Zhang, Richard Jiang
Pubblicato in: 2024
Editore: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.36227/TECHRXIV.170421894.45150592/V1

FineWeb2: A sparkling update with 1000s of languages

Autori: Guilherme Penedo, Hynek Kydlíček, Vinko Sabolčec, Bettina Messmer, Negar Foroutan, Martin Jaggi, Leandro von Werra, Thomas Wolf
Pubblicato in: github open source release
Editore: github open source release

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

Autori: Trizna, D., Demetrio, L., Biggio, B., & Roli, F.
Pubblicato in: 2024, ISSN 2402-18329
Editore: ArXiv
DOI: 10.48550/arXiv.2402.18329

epfLLM Megatron-LLM

Autori: 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
Editore: GitHub

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs

Autori: Thierry Bossy, Julien Vignoud, Tahseen Rabbani, Juan R Troncoso Pastoriza, Martin Jaggi
Pubblicato in: arXiv
Editore: arXiv
DOI: 10.48550/ARXIV.2502.05087

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

Autori: Dongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi
Pubblicato in: arXiv
Editore: arXiv
DOI: 10.48550/ARXIV.2409.13931

Evaluating Language Models for Mathematics through Interactions

Autori: 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
Pubblicato in: ISSN 2306-01694
Editore: arXiv
DOI: 10.1073/PNAS.2318124121

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

Autori: Cinà, A.E., Villani, F., Pintor, M., Schönherr, L., Biggio, B., Pelillo, M.,
Pubblicato in: 2024, ISSN 2402-01879
Editore: ArXiv
DOI: 10.48550/arXiv.2402.01879

From Managers to Machines: A Reply to Respondents

Autori: Karen Yeung
Editore: Tilburg Law Review
DOI: 10.5334/TILR.308

Transfer learning from inorganic materials to ivory detection

Autori: A. Aghasanli, P. Angelov, D. Kangin, J. Kerns and R. Shepherd
Pubblicato in: Scientific Reports
Editore: Scientific Reports

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

Autori: Nathalie A. Smuha, Karen Yeung
Pubblicato in: 2024
Editore: Elsevier BV
DOI: 10.2139/SSRN.4874852

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

Autori: Daqian Shao, Lukas Fesser, Marta Kwiatkowska
Pubblicato in: Technical report, paper under submission, 2023
Editore: N/A
DOI: 10.48550/arXiv.2401.05338

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

Autori: Ruben Perez Tito
Pubblicato in: 2023, ISBN 978-84-124793-5-5
Editore: Ediciones Gráficas Rey

È in corso la ricerca di dati su OpenAIRE...

Risultati finali

Pubblicazioni

Condividi questa pagina Condividi questa pagina sui social network

Scarica il PDF Scarica il contenuto della pagina