Adversarial attacks in consensus-based multi-agent reinforcement learning

2021/03/11 by Martin Figura, Figura, Martin, Krishna Chaitanya Kosaraju +3 · 2 citations
Agricultural and Biological Sciences · Computer Science · Engineering · Mathematics · #Insect and Pesticide Research #cs.AI #cs.LG #cs.SY #eess.SY #stat.ML

paper · pdf · doi:10.48550/arxiv.2103.06967

arxiv created 2021/03/11 · arxiv updated 2021/03/15

Abstract

Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature. In this work, we study the effect of adversarial attacks on a network that employs a consensus-based MARL algorithm. We show that an adversarial agent can persuade all the other agents in the network to implement policies that optimize an objective that it desires. In this sense, the standard consensus-based MARL algorithms are fragile to attacks.

Cited by

• Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space
• Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach

Related

• An Algorithm For Adversary Aware Decentralized Networked MARL
• Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
• On the Robustness of Cooperative Multi-Agent Reinforcement Learning
• Attacking c-MARL More Effectively: A Data Driven Approach
• Adversarial Attacks in Cooperative AI