A COMPREHENSIVE TRUSTWORTHY FRAMEWORK FOR CONNECTED MACHINE LEARNING AND SECURE INTERCONNECTED AI SOLUTIONS

Informazioni relative al progetto

CoEvolution

ID dell’accordo di sovvenzione: 101168560

DOI

10.3030/101168560

Data della firma CE 6 Luglio 2024

Data di avvio 1 Novembre 2024

Data di completamento 31 Ottobre 2027

Finanziato da

• Civil Security for Society

Costo totale

€ 5 999 688,75

Contributo UE

€ 5 999 688,75

Coordinato da

EREVNITIKO PANEPISTIMIAKO INSTITOUTO SYSTIMATON EPIKOINONION KAI YPOLOGISTON
Greece

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 .

Pubblicazioni

Conference proceedings (15)

Online Curvature-Aware Replay: Leveraging 2nd Order Information for Online Continual Learning

Autori: Urettini, Edoardo and Carta, Antonio
Pubblicato in: Proceedings of the 42nd International Conference on Machine Learning, 2025, ISSN 2640-3498
Editore: PMLR

A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions

Autori: Antonios Makris, Christos Dousis, Emmanouil Kritharakis, Stavros Bouras, Konstantinos Tserpes
Pubblicato in: 8th International Workshop on Intelligent Systems for the Internet of Things, 2026
Editore: arxiv/ IEEE Explore
DOI: 10.48550/ARXIV.2605.11010

Efficient Model-Based Purification Against Adversarial Attacks for LiDAR Segmentation

Autori: Alexandros Gkillas, Ioulia Kapsali, Nikos Piperigkos, Aris S. Lalos
Pubblicato in: 2025 IEEE International Conference on Image Processing, 2025
Editore: IEEE
DOI: 10.48550/ARXIV.2508.19290

Less is more? an ablation study on AutoAttack for adversarial robustness evaluation

Autori: Luca Melis, Luca Scionis, Fabio Brau, Maura Pintor, Battista Biggio
Pubblicato in: 2025 International Conference on Machine Learning and Cybernetics (ICMLC), 2025
Editore: IEEE
DOI: 10.1109/ICMLC66258.2025.11280165

CoEvolution: A Comprehensive Trustworthy Framework For Connected Machine Learning And Secure Interconnected AI Solutions

Autori: Antonios Makris, Apostolos Fournaris, Anita Aghaie, Ioannis Arakas, Anna Maria Anaxagorou, Ioannis Arapakis, Davide Bacciu, Battista Biggio, Georgios Bouloukakis, Stavros Bouras, Arne Bröring, Antonio Carta, Marco Caselli, Olympia Giannakopoulou, Nikolaos Gkatzios, Alexandros Gkillas, Evangelos Haleplidis, Sotiris Ioannidis, Eleni-Maria Kalogeraki, Panagiotis Karantzias, Emmanouil Kritharakis, Aris Lalos, David Lenk, Stella Markopoulou, Entrit Metai, Andreas Miaoudakis, Haralambos Mouratidis, Jihane Najar, Theodor Panagiotakopoulos, Bernhard Peischl, Maura Pintor, Nikos Piperigkos, Vassilis Prevelakis, Carlos Segura, Georgios Spanoudakis, Orestis Tsirakis, Omar Veledar, Konstantinos Tserpes
Pubblicato in: 2025 IEEE International Conference on Cyber Security and Resilience (CSR), 2025
Editore: IEEE
DOI: 10.1109/CSR64739.2025.11130091

Improving UWB Multipath Error Correction inTDoA Systems Using TWR-Derived Models

Autori: Phuong Duong, Broering Arne
Pubblicato in: 15th International Conference on Indoor Positioning and Indoor Navigation, 2025
Editore: IEEE Explore
DOI: 10.1109/IPIN66788.2025.11212961

Robustifying 3D Perception via Least-Squares Graphs for Multi-Agent Object Tracking

Autori: Maria Damanaki, Ioulia Kapsali, Nikos Piperigkos, Alexandros Gkillas, Aris S. Lalos
Pubblicato in: 51st Annual Conference of the IEEE Industrial Electronics Society
Editore: IEEE
DOI: 10.48550/ARXIV.2507.04762

Benchmarking ensemble-based black-box transfer attacks

Autori: Fabio Brau, Maura Pintor, Antonio Emanuele Cinà, Luca Scionis, Luca Oneto, Fabio Roli, Battista Biggio
Pubblicato in: NEURIPS - 39th Neural Information Processing Systems, 2025
Editore: NEURIPS

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps

Autori: Stavros Bouras, Ioannis Korontanis, Antonios Makris, Konstantinos Tserpes
Pubblicato in: 1st Workshop on Secure and Intelligent Data Spaces (SIDS 2026), 2026
Editore: IEEE
DOI: 10.48550/ARXIV.2605.15249

Replay-free Online Continual Learning with Self-Supervised MultiPatches

Autori: Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa, Joost van de Weijer, Antonio Carta
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/ARXIV.2502.09140

SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models

Autori: Giorgio Piras, Raffaele Mura, Fabio Brau, Luca Oneto, Fabio Roli, Battista Biggio
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, Numero 40, 2026, ISSN 2374-3468
Editore: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/AAAI.V40I39.40551

A Comparative Analysis of Active Learning Strategies for Android Malware Detection

Autori: Cristian Manca, Luca Minnei, Maura Pintor, Fabio Brau, Battista Biggio
Pubblicato in: International Conference on Machine Learning and Cybernetics, ICMLC 2025, Bali, Indonesia 12-15 July 2025, 2025
Editore: IEEE
DOI: 10.1109/ICMLC66258.2025.11280195

FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning

Autori: Emmanouil Kritharakis, Antonios Makris, Dusan Jakovetic, Konstantinos Tserpes
Pubblicato in: 2025 3rd International Conference on Federated Learning Technologies and Applications (FLTA), 2025
Editore: IEEE
DOI: 10.1109/FLTA67013.2025.11336535

Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering

Autori: Emmanouil Kritharakis, Antonios Makris, Dusan Jakovetic, Konstantinos Tserpes
Pubblicato in: WAFL Workshop @ ECML-PKDD 2025, 2025
Editore: Springer

CLA: Latent Alignment for Online Continual Self-Supervised Learning

Autori: Giacomo Cignoni, Andrea Cossu, Alexandra Gomez-Villa, Joost van de Weijer, Antonio Carta
Pubblicato in: Proceedings of The 4th Conference on Lifelong Learning Agents, 2025, ISSN 2640-3498
Editore: PMLR
DOI: 10.48550/ARXIV.2507.10434

Peer reviewed articles (4)

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, 2026, ISSN 0031-3203
Editore: Elsevier BV
DOI: 10.1016/J.PATCOG.2025.112519

Diffusion Models for Tabular Data Imputation and Synthetic Data Generation

Autori: Mario Villaizán-Vallelado, Matteo Salvatori, Carlos Segura, Ioannis Arapakis
Pubblicato in: ACM Transactions on Knowledge Discovery from Data, 2025, ISSN 1556-4681
Editore: ACM
DOI: 10.1145/374243

Pattern Recognition

Autori: Srishti Gupta , Daniele Angioni, Maura Pintor, Ambra Demontis, Lea Schönherr, Fabio Roli, Battista Biggio
Pubblicato in: Pattern Recognition, 2026, ISSN 0031-3203
Editore: Pergamon Press
DOI: 10.1016/J.PATCOG.2025.112441

Conditional Diffusion Models: A Survey of Techniques, Applications, and Challenges

Autori: Theodor Panagiotakopoulos, Sotiris Kotsiantis, Alexandros Gkillas, Aris S. Lalos
Pubblicato in: IEEE Access, Numero 13, 2025, ISSN 2169-3536
Editore: IEEE
DOI: 10.1109/ACCESS.2025.3625094