Multi-Agent Adversarial Training Using Diffusion Learning
Ying Cao (École polytechnique fédérale de Lausanne ‐ EPFL); Elsa Rizk (EPFL); Stefan Vlaski (Imperial College London); Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)
-
Members: FreeSPS
IEEE Members: $11.00
Non-members: $15.00
07 Jun 2023
This work focuses on adversarial learning over graphs. We propose a general adversarial training framework for multi-agent systems using diffusion learning. We analyze the convergence properties of the proposed scheme for convex optimization problems, and illustrate its enhanced robustness to adversarial attacks.
