Multi-Agent Adversarial Training Using Diffusion Learning

Autor:	Cao, Ying, Rizk, Elsa, Vlaski, Stefan, Sayed, Ali H.
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Multiagent Systems
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.01936 Zobrazit plný text záznamu View this record from Arxiv