CORDIS Project
Funding breakdown and partner intelligence are Premium
Sign in and upgrade to Premium for EU contribution totals, consortium analytics, OpenAlex research context, and AI summaries. · 0 consortium intelligence fields visible of 1
Start free • Cancel anytime • 14-day refund guarantee
This project focuses on identifying and mitigating vulnerabilities in artificial intelligence algorithms through mathematical analysis. It aims to develop new methodologies to understand adversarial attacks and enhance the robustness of AI systems.
From a numerical analysis perspective I will identify, quantify and mitigate vulnerabilities in current artificial intelligence (AI) algorithms.Novel mathematical research will emerge along six overlapping axes:Inevitability: rigorously understand the inescapable endgame of the attack-versus-defence paradigm.
Under what conditions is it inevitable that adversaries willsucceed?
Formalizing such conditions will allow us to understand and, where possible, overcome current AI instabilities.Editabili…
THE UNIVERSITY OF EDINBURGH
Partner organizations (coordinator is shown above), with normalized type and CORDIS activity type. Guests see up to 4 partners.
Similar projects, consortium collaboration history, frequent partners, and OpenAlex research context.
Guests see up to 5 topics.
Guests see up to 5 keywords.
