TY - GEN
T1 - CoEvolution
T2 - 5th IEEE International Conference on Cyber Security and Resilience, CSR 2025
AU - Makris, Antonios
AU - Fournaris, Apostolos
AU - Aghaie, Anita
AU - Arakas, Ioannis
AU - Anaxagorou, Anna Maria
AU - Arapakis, Ioannis
AU - Bacciu, Davide
AU - Biggio, Battista
AU - Bouloukakis, Georgios
AU - Bouras, Stavros
AU - Bröring, Arne
AU - Carta, Antonio
AU - Caselli, Marco
AU - Giannakopoulou, Olympia
AU - Gkatzios, Nikolaos
AU - Gkillas, Alexandros
AU - Haleplidis, Evangelos
AU - Ioannidis, Sotiris
AU - Kalogeraki, Eleni Maria
AU - Karantzias, Panagiotis
AU - Kritharakis, Emmanouil
AU - Lalos, Aris
AU - Lenk, David
AU - Markopoulou, Stella
AU - Metai, Entrit
AU - Miaoudakis, Andreas
AU - Mouratidis, Haralambos
AU - Najar, Jihane
AU - Panagiotakopoulos, Theodor
AU - Peischl, Bernhard
AU - Pintor, Maura
AU - Piperigkos, Nikos
AU - Prevelakis, Vassilis
AU - Segura, Carlos
AU - Spanoudakis, Georgios
AU - Tsirakis, Orestis
AU - Veledar, Omar
AU - Tserpes, Konstantinos
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - 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.
AB - 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.
KW - adversarial attacks
KW - ai model bills of material
KW - risk assessment
KW - robustness
KW - security
KW - threat models
UR - https://www.scopus.com/pages/publications/105016185379
U2 - 10.1109/CSR64739.2025.11130091
DO - 10.1109/CSR64739.2025.11130091
M3 - Conference contribution
AN - SCOPUS:105016185379
T3 - Proceedings of the 2025 IEEE International Conference on Cyber Security and Resilience, CSR 2025
SP - 838
EP - 845
BT - Proceedings of the 2025 IEEE International Conference on Cyber Security and Resilience, CSR 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 August 2025 through 6 August 2025
ER -