Full Program

CoEvolution: A comprehensive trustworthy framework for connected machine learning and secure interconnected AI solutions

Summary:

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.

Author(s):

Antonios Makris    
School of Electrical and Computer Engineering, National Technical University of Athens
Greece

Apostolos Fournaris    
Industrial Systems Institute, Research Center ATHENA
Greece

Anita Aghaie    
Siemens AG
Germany

Ioannis Arapakis    
Telefónica Scientific Research
Spain

Battista Biggio    
Department of Electrical and Electronic Engineering, University of Cagliari
Italy

Georgios Bouloukakis    
Télécom SudParis, Institut Polytechnique de Paris, France
France

Stavros Bouras    
School of Electrical and Computer Engineering, National Technical University of Athens
Greece

Arne Bröring    
Siemens AG
Germany

Marco Caselli    
Siemens AG
Germany

Nikolaos Gkatzios    
AEGIS IT RESEARCH GMBH
Germany

Evangelos Haleplidis    
Industrial Systems Institute, Research Center ATHENA
Greece

Emmanouil Kritharakis    
School of Electrical and Computer Engineering, National Technical University of Athens
Greece

David Lenk    
AVL List GmbH
Austria

Stella Markopoulou    
AEGIS IT RESEARCH GMBH
Germany

Jihane Najar    
AEGIS IT RESEARCH GMBH
Germany

Maura Pintor    
Department of Electrical and Electronic Engineering, University of Cagliari
Italy

Vassilis Prevelakis    
AEGIS IT RESEARCH GMBH
Germany

Carlos Segura    
Telefónica Scientific Research
Spain

Omar Veledar    
Beevadoo e.U.
Austria

Konstantinos Tserpes    
School of Electrical and Computer Engineering, National Technical University of Athens
Greece