CoEvolution: A Comprehensive Trustworthy Framework For Connected Machine Learning And Secure Interconnected AI Solutions
The contemporary AI landscape demands a holistic framework to ensure security across the entire AI supply chain and lifecycle. Despite the availability of existing adversarial attack techniques, an end-to-end solution for identifying threats, vulnerabilities, and risks is still lacking. Despite EU initiatives like the AI Act promoting safety and trustworthiness in AI, it lacks a system for managing weaknesses within a networked AI supply chain. This paper introduces CoEvolution, which aspires to address this gap by implementing a complete Security, Trust, and Robustness (STR) assessment solution, capable of addressing evolving AI cybersecurity threats. CoEvolution proposes a universal hub for STR risk assessment and security assurance, aligned with MLDevOps practices and EU AI regulatory frameworks. It introduces innovative AI model descriptions, including an AI Model Bill of Materials, coupled with security monitoring and context awareness. CoEvolution seeks to ensure compliance with EU directives on trust, fairness, data governance, and GDPR guidelines.
Authors
- Anita Aghaie (ORCID: https://orcid.org/0000-0003-2470-3408)
- Nikos Piperigkos (ORCID: https://orcid.org/0000-0003-0262-7619)
- I. Arapakis (ORCID: https://orcid.org/0000-0002-4212-0890)
- Eleni-Maria Kalogeraki (ORCID: https://orcid.org/0000-0003-2811-5021)
- Andreas Miaoudakis
- Battista Biggio (ORCID: https://orcid.org/0000-0001-7752-509X)
- Haralambos Mouratidis (ORCID: https://orcid.org/0000-0002-2599-0712)
- Konstantinos Tserpes (ORCID: https://orcid.org/0000-0001-5183-1443)
- Maura Pintor (ORCID: https://orcid.org/0000-0002-1944-2875)
- Olympia Giannakopoulou (ORCID: https://orcid.org/0000-0003-4473-2070)
- Emmanouil Kritharakis
- Georgios Spanoudakis
- Αλέξανδρος Γκίλλας (ORCID: https://orcid.org/0000-0001-5339-2018)
- Omar Veledar (ORCID: https://orcid.org/0000-0002-8302-7721)
- Nikolaos Gkatzios (ORCID: https://orcid.org/0000-0002-0908-8913)
- Entrit Metai
- Antonio Carta (ORCID: https://orcid.org/0000-0002-0003-2323)
- S. Bouras
- Davide Bacciu (ORCID: https://orcid.org/0000-0001-5213-2468)
- Arne Bröring (ORCID: https://orcid.org/0000-0002-1181-3897)
- Vassilis Prevelakis (ORCID: https://orcid.org/0000-0001-6176-1637)
- Stella Markopoulou (ORCID: https://orcid.org/0000-0001-9819-3143)
- Apostolos P. Fournaris (ORCID: https://orcid.org/0000-0002-4758-2349)
- Bernhard Peischl (ORCID: https://orcid.org/0000-0002-5440-7223)
- Theodor Panagiotakopoulos (ORCID: https://orcid.org/0000-0003-4044-6018)
- Antonios Makris (ORCID: https://orcid.org/0000-0003-0514-4292)
- Georgios Bouloukakis (ORCID: https://orcid.org/0000-0003-0109-9527)
- Evangelos Haleplidis (ORCID: https://orcid.org/0009-0002-7689-6483)
- Aris S. Lalos (ORCID: https://orcid.org/0000-0003-0511-9302)
- Anna Maria Anaxagorou (ORCID: https://orcid.org/0009-0003-4111-7336)
- Jihane Najar
- Marco Caselli (ORCID: https://orcid.org/0000-0003-4883-797X)
- Sotiris Ioannidis (ORCID: https://orcid.org/0009-0002-0682-0475)
- Ioannis Arakas
- Orestis Tsirakis
- Carlos Segura (ORCID: https://orcid.org/0000-0001-5867-281X)
- Panagiotis Karantzias
- David Lenk
Institutions
- University of Pisa (IT)
- Siemens (Germany) (DE)
- University of Cagliari (IT)
- National Technical University of Athens (GR)
- University of Patras (GR)
- Hellenic Mediterranean University (GR)
- University of Cyprus (CY)
- BEST - Bioenergy and Sustainable Technologies (Austria) (AT)
- Telefonica Research and Development (ES)
- Industrial Systems Institute (GR)
- Dynavax Technologies (Germany) (DE)
- BH Consulting (Ireland) (IE)
- Anstalt für Verbrennungskraftmaschinen List (Austria) (AT)
- Technische Universität Braunschweig (DE)
Publication Details
- Published
- 2025-08-04
- DOI
- https://doi.org/10.1109/csr64739.2025.11130091
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- HORIZON EUROPE Framework Programme