Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning

Abstract

Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning (AML) attacks. Execution-time AML attacks against MARL are complex due to effects that propagate across time and between agents. To understand the interaction between AML and MARL, this survey covers attacks and defences for MARL, Multi-Agent Learning (MAL), and Deep Reinforcement Learning (DRL). This survey proposes a novel perspective on AML attacks based on attack vectors. This survey also proposes a framework that addresses gaps in current modelling frameworks and enables the comparison of different attacks against MARL. Lastly, the survey identifies knowledge gaps and future avenues of research.