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

Coevolution is a European Union-funded project under the Horizon Europe research and innovation program, bringing together 15 partners from various countries.
The main objective is to focus on establishing a comprehensive security and risk assessment process for AI models throughout their lifecycle, ensuring security-by-design under various paradigms (single, collaborative, or interconnected AI agents). A Security, Trust, and Robustness Defense Framework will be developed to align with EU AI regulations.
The initiative aims to create a CoEvolution hub for secure AI supply chains, validated through complex pilots, and culminate in a sustainable business plan. In the Coevolution project, AVISENSE plays a key role as the leader of WP6, overseeing multiple technical tasks and co-leading the automotive pilot alongside AVL.
The company is responsible for developing adversarial attack strategies and designing robust defense mechanisms for both single-agent and collaborative perception scenarios in autonomous systems.