Multi-Agent Adversarial Training Using Diffusion Learning
Machine Learning
2023-03-06 v1 Artificial Intelligence
Multiagent Systems
Abstract
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.
Cite
@article{arxiv.2303.01936,
title = {Multi-Agent Adversarial Training Using Diffusion Learning},
author = {Ying Cao and Elsa Rizk and Stefan Vlaski and Ali H. Sayed},
journal= {arXiv preprint arXiv:2303.01936},
year = {2023}
}