European Lighthouse on Secure and Safe AI

Informations projet

ELSA

N° de convention de subvention: 101070617

DOI

10.3030/101070617

Date de signature de la CE 23 Juin 2022

Date de début 1 Septembre 2022

Date de fin 31 Août 2026

Financé au titre de

• Digital, Industry and Space

Coût total

€ 7 434 058,75

Contribution de l’UE

€ 7 434 058,50

Coordonné par

CISPA - HELMHOLTZ-ZENTRUM FUR INFORMATIONSSICHERHEIT GGMBH
Germany

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

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.

Publications

Peer reviewed articles (13)

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

Auteurs: Luca Oneto, Sandro Ridella, Davide Anguita
Publié dans: Neurocomputing, Numéro 592, 2024, ISSN 0925-2312
Éditeur: Elsevier BV
DOI: 10.1016/J.NEUCOM.2024.127798

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

Auteurs: Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Sebastiano Vascon, Werner Zellinger, Bernhard A. Moser, Alina Oprea, Battista Biggio, Marcello Pelillo, Fabio Roli
Publié dans: ACM Computing Surveys, 2023, ISSN 0360-0300
Éditeur: Association for Computing Machinery
DOI: 10.1145/3585385

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

Auteurs: Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Andrea Pilzer, Rita Cucchiara
Publié dans: Computer Vision and Image Understanding, Numéro 252, 2025, ISSN 1077-3142
Éditeur: Elsevier BV
DOI: 10.1016/J.CVIU.2025.104294

Neuron Activation Pattern and Applications

Auteurs: Z. Jiang, P. Angelov, D. Kangin, …
Publié dans: Tech Rxiv, IEEE, 2024, ISSN 0000-0000
Éditeur: 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?

Auteurs: Karen Yeung
Publié dans: Prometheus, 2023, ISSN 1470-1030
Éditeur: Pluto Journals
DOI: 10.13169/prometheus.39.1.0008

Delve Into Neural Activations: Toward Understanding Dying Neurons

Auteurs: Ziping Jiang, Yunpeng Wang, Chang-Tsun Li, Plamen Angelov, Richard Jiang
Publié dans: IEEE Transactions on Artificial Intelligence, Numéro 4, 2024, ISSN 2691-4581
Éditeur: IEEE
DOI: 10.1109/TAI.2022.3180272

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

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

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

Auteurs: Leonardo Iurada; Silvia Bucci; Timothy M. Hospedales; Tatiana Tommasi
Publié dans: IEEE Access, 2024, ISSN 2169-3536
Éditeur: IEEE
DOI: 10.1109/ACCESS.2024.3383841

Investigating over-parameterized randomized graph networks

Auteurs: Giovanni Donghi, Luca Pasa, Luca Oneto, Claudio Gallicchio, Alessio Micheli, Davide Anguita, Alessandro Sperduti, Nicolò Navarin
Publié dans: Neurocomputing, Numéro 606, 2024, ISSN 0925-2312
Éditeur: Elsevier BV
DOI: 10.1016/J.NEUCOM.2024.128281

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

Auteurs: Filippo Galli, Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi, Tommaso Cucinotta
Publié dans: Springer Nature Computer Science, 2023, ISSN 2661-8907
Éditeur: Springer Nature
DOI: 10.1007/s42979-023-02292-0

Nebula: Self-Attention for Dynamic Malware Analysis

Auteurs: Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Fabio Roli
Publié dans: IEEE Transactions on Information Forensics and Security, Numéro 19, 2025, ISSN 1556-6013
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TIFS.2024.3409083

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

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

Hierarchical multimodal transformers for Multipage DocVQA

Auteurs: Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny
Publié dans: Pattern Recognition, Numéro 144, 2023, ISSN 0031-3203
Éditeur: Elsevier BV
DOI: 10.1016/J.PATCOG.2023.109834

Conference proceedings (48)

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

Auteurs: Luca Barsellotti, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Publié dans: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Éditeur: IEEE
DOI: 10.1109/CVPR52733.2024.00354

Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks

Auteurs: Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev
Publié dans: PLDI'23 (Proceedings of the ACM on Programming Languages), 2023, ISSN 2475-1421
Éditeur: """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

Auteurs: Pier Giuseppe Sessa, Pierre Laforgue, Nicolò Cesa-Bianchi, Andreas Krause
Publié dans: Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023
Éditeur: Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

Is Mamba Capable of In-Context Learning?

Auteurs: Riccardo Grazzi, Julien Niklas Siems, Simon Schrodi, Thomas Brox, Frank Hutter
Publié dans: Sumbitted to AutoML24 Conference, 2024
Éditeur: Paper under double-blind review
DOI: 10.48550/arXiv.2402.03170

Improving Fairness via Intrinsic Plasticity in Echo State Networks

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

Unsupervised Domain Adaptation within Deep Foundation Latent Spaces

Auteurs: P. Angelov, D. Kangin
Publié dans: ICLR Workshop on Mathematical and Empirical understanding of FM, 2024
Éditeur: ICLR Workshop on Mathematical and Empirical understanding of FM

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

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

DRCFS: Doubly Robust Causal Feature Selection

Auteurs: Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer
Publié dans: ICML 2023: Fortieth International Conference on Machine Learning, 2023
Éditeur: JMLR.org
DOI: 10.48550/arXiv.2306.07024

Data Drift in Android Malware Detection

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

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

Auteurs: Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick Pérez, Matthieu Cord
Publié dans: European Conference on Computer Vision (ECCV) 2024, 2024
Éditeur: European Conference on Computer Vision (ECCV) 2024
DOI: 10.48550/ARXIV.2312.09231

Fuzzy Detectors Against Adversarial Attacks

Auteurs: Y. Li, P. Angelov, N. Suri
Publié dans: IEEE Symposium Series on Computational Intelligence, 2023
Éditeur: IEEE Symposium Series on Computational Intelligence

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

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

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

Auteurs: Andreas Athanasiou, Kangsoo Jung, Catuscia Palamidessi
Publié dans: Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, 2025
Éditeur: ACM
DOI: 10.1145/3658644.3691411

A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets

Auteurs: Ossi Räisä, Antti Honkela
Publié dans: AISTATS 2025, 2025
Éditeur: AISTATS 2025
DOI: 10.48550/ARXIV.2402.03985

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

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

Expressivity of ReLU-Networks under Convex Relaxations

Auteurs: Maximilian Baader, Mark Niklas Müller, Yuhao Mao, Martin Vechev
Publié dans: ICLR'24, 2023
Éditeur: ICLR
DOI: 10.48550/arXiv.2311.04015

Adversarial Causal Bayesian Optimization

Auteurs: S. Sussex, P. G. Sessa, A. Makarova, A. Krause
Publié dans: International Conference on Learning Representations (ICLR), 2023
Éditeur: ICLR
DOI: 10.48550/arXiv.2307.16625

STEP - Towards Structured Scene-Text Spotting

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

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

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

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

Auteurs: Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Publié dans: IEEE CVPR 2024, 2024
Éditeur: IEEE CVPR 2024

Noise-Aware Differentially Private Variational Inference

Auteurs: Talal Alrawajfeh, Joonas Jälkö, Antti Honkela
Publié dans: AISTATS 2025, 2025
Éditeur: AISTATS 2025
DOI: 10.48550/ARXIV.2410.19371

A Simple Recipe for Language-guided Domain Generalized Segmentation

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

Vision-Based Landing Guidance Through Tracking and Orientation Estimation

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

Synthcap: Augmenting transformers with synthetic data for image captioning

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

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

Auteurs: Riccardo Grazzi; Saverio Salzo; Massimiliano Pontil
Publié dans: Journal Of Machine Learning Research, 2024, ISSN 2403-11687
Éditeur: 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

Auteurs: Daniel Marta, Simon Holk, Miguel Vasco, Jens Lundell, Timon Homberger, Finn Busch, Olov Andersson, Danica Kragic, Iolanda Leite
Publié dans: 2025 International Conference on Robotics and Automation, 2025
Éditeur: IEEE

Cooperative online learning with feedback graphs

Auteurs: Nicolò Cesa-Bianchi, Tommaso Cesari, and Riccardo Della Vecchia
Publié dans: Transactions on Machine Learning Research (06/2024), 2024
Éditeur: Transactions on Machine Learning Research (06/2024)

Certifiers Make Neural Networks Vulnerable to Availability Attacks

Auteurs: Tobias Lorenz, Marta Kwiatkowska, Mario Fritz
Publié dans: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, 2025
Éditeur: ACM
DOI: 10.1145/3605764.3623917

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

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

Mitigating Robustness Bias: Theoretical Results and Empirical Evidences

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

Lecture Notes in Computer Science

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

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

Auteurs: Mohamed Ali Souibgui, Sanket Biswas, Andres Mafla, Ali Furkan Biten, Alicia Fornés, Yousri Kessentini, Josep Lladós, Lluis Gomez, Dimosthenis Karatzas
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 37, 2023, ISSN 2374-3468
Éditeur: 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

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

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

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

ModSec-Learn: Boosting ModSecurity with Machine Learning

Auteurs: Christian Scano, Giuseppe Floris, Biagio Montaruli, Luca Demetrio, Andrea Valenza, Luca Compagna, Davide Ariu, Luca Piras, Davide Balzarotti, Battista Biggio
Publié dans: Lecture Notes in Networks and Systems, Distributed Computing and Artificial Intelligence, Special Sessions I, 21st International Conference, 2025
Éditeur: 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

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

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

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

Distributionally Robust Model-based Reinforcement Learning with Large State Spaces

Auteurs: S.S. Ramesh, P. G. Sessa, Y. Hu, A. Krause, I. Bogunovic
Publié dans: International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Éditeur: AISTATS
DOI: 10.48550/arXiv.2309.02236

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

Auteurs: Antonio Alliegro, Francesco Cappio Borlino, Tatiana Tommasi
Publié dans: Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Datasets and Benchmarks Track, 2022, ISBN 9781713871088
Éditeur: NeurIPS 2022

Hyperparameters in Score-Based Membership Inference Attacks

Auteurs: Gauri Pradhan, Joonas Jälkö, Marlon Tobaben, Antti Honkela
Publié dans: SaTML 2025, 2025
Éditeur: SaTML 2025
DOI: 10.48550/ARXIV.2502.06374

The BRAVO Semantic Segmentation Challenge Results in UNCV2024

Auteurs: 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
Publié dans: European Conference on Computer Vision (ECCV) 2024, 2024
Éditeur: European Conference on Computer Vision (ECCV) 2024
DOI: 10.48550/ARXIV.2409.15107

Learning Counterfactually Invariant Predictors

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

Fair Empirical Risk Minimization Revised

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

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

Auteurs: Yuchong Zhang, Miguel Vasco, Mårten Björkman, Danica Kragic
Publié dans: International Conference on Human-Computer Interaction (HCII) 2024, 2024
Éditeur: Springer
DOI: 10.48550/ARXIV.2403.18616

Edge Implementation of Unsupervised Self-evolving Vision Classifier

Auteurs: P. Angelov, A. Aghasanli
Publié dans: IEEE International Conference on Evolving and Adaptive Intelligent Systems 2024, 2024
Éditeur: IEEE International Conference on Evolving and Adaptive Intelligent Systems 2024
DOI: 10.1109/EAIS58494.2024.10570024

Human Uncertainty in Concept-Based AI Systems

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

Automated Classification of Model Errors on ImageNet

Auteurs: Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
Publié dans: NeurIPS'23, 2023
Éditeur: NeurIPS
DOI: 10.48550/arXiv.2401.02430

DocILE Benchmark for Document Information Localization and Extraction

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

Other (6)

DPVIm: Differentially Private Variational Inference Improved

Auteurs: Joonas Jälkö, Lukas Prediger, Antti Honkela, Samuel Kaski
Publié dans: TMLR 9/2023, 2023
Éditeur: TMLR 9/2023

On Neuron Activation Pattern and Applications

Auteurs: Ziping Jiang, Plamen Angelov, Dmitry Kangin, Zhaonian Zhang, Richard Jiang
Publié dans: 2024
Éditeur: 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

Auteurs: Trizna, D., Demetrio, L., Biggio, B., & Roli, F.
Publié dans: 2024, ISSN 2402-18329
Éditeur: ArXiv
DOI: 10.48550/arXiv.2402.18329

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

Auteurs: Cinà, A.E., Villani, F., Pintor, M., Schönherr, L., Biggio, B., Pelillo, M.,
Publié dans: 2024, ISSN 2402-01879
Éditeur: ArXiv
DOI: 10.48550/arXiv.2402.01879

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

Auteurs: Nathalie A. Smuha, Karen Yeung
Publié dans: 2024
Éditeur: Elsevier BV
DOI: 10.2139/SSRN.4874852

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

Auteurs: Daqian Shao, Lukas Fesser, Marta Kwiatkowska
Publié dans: Technical report, paper under submission, 2023
Éditeur: 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

Auteurs: Ruben Perez Tito
Publié dans: 2023, ISBN 978-84-124793-5-5
Éditeur: Ediciones Gráficas Rey