European Lighthouse on Secure and Safe AI

Informacje na temat projektu

ELSA

Identyfikator umowy o grant: 101070617

DOI

10.3030/101070617

Data podpisania przez KE 23 Czerwca 2022

Data rozpoczęcia 1 Września 2022

Data zakończenia 31 Sierpnia 2026

Finansowanie w ramach

• Digital, Industry and Space

Koszt całkowity

€ 7 434 058,75

Wkład UE

€ 7 434 058,50

Koordynowany przez

CISPA - HELMHOLTZ-ZENTRUM FUR INFORMATIONSSICHERHEIT GGMBH
Germany

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

Data sets, microdata, etc (1)

Benchmark Datasets

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

Documents, reports (7)

Report on Privacy and Infrastructures Grand Challenge and Benchmarking Metrics

This report will summarise the results of Task 2.1.

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 Network and Communication Activities 1

Report on Network and Communication activities 1.

Use Cases Activity Report 1

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

Websites, patent fillings, videos etc. (1)

Visual Identity, Style and Communication Guidelines

Visual identity, style and communication guidelines.

Publikacje

Peer reviewed articles (13)

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

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, 2023, ISSN 0360-0300
Wydawca: Association for Computing Machinery
DOI: 10.1145/3585385

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

Neuron Activation Pattern and Applications

Autorzy: Z. Jiang, P. Angelov, D. Kangin, …
Opublikowane w: Tech Rxiv, IEEE, 2024, ISSN 0000-0000
Wydawca: Tech Rxiv, IEEE
DOI: 10.36227/TECHRXIV.170421894.45150592

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

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

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

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

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

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

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

Conference proceedings (48)

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

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

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)

Is Mamba Capable of In-Context Learning?

Autorzy: Riccardo Grazzi, Julien Niklas Siems, Simon Schrodi, Thomas Brox, Frank Hutter
Opublikowane w: Sumbitted to AutoML24 Conference, 2024
Wydawca: Paper under double-blind review
DOI: 10.48550/arXiv.2402.03170

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

Unsupervised Domain Adaptation within Deep Foundation Latent Spaces

Autorzy: P. Angelov, D. Kangin
Opublikowane w: ICLR Workshop on Mathematical and Empirical understanding of FM, 2024
Wydawca: ICLR Workshop on Mathematical and Empirical understanding of FM

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

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

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

"""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

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

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

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

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

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

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

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

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

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

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

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

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)

Certifiers Make Neural Networks Vulnerable to Availability Attacks

Autorzy: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Opublikowane w: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2025
Wydawca: ACM
DOI: 10.1145/3605764.3623917

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Other (6)

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

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

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

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

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

Thesis and dissertations (1)

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