Multi-Agent Adversarial Training Using Diffusion Learning

03/03/2023

∙

by   Ying Cao, et al.

∙

0

∙

share

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.