SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
This work addresses security vulnerabilities in MARL for real-world applications, but it is incremental as it builds on existing AML research.
The paper surveys adversarial machine learning attacks and defenses in multi-agent reinforcement learning, proposing new frameworks to model attack vectors and identify research gaps.
Multi-Agent Reinforcement Learning (MARL) is vulnerable to Adversarial Machine Learning (AML) attacks and needs adequate defences before it can be used in real world applications. We have conducted a survey into the use of execution-time AML attacks against MARL and the defences against those attacks. We surveyed related work in the application of AML in Deep Reinforcement Learning (DRL) and Multi-Agent Learning (MAL) to inform our analysis of AML for MARL. We propose a novel perspective to understand the manner of perpetrating an AML attack, by defining Attack Vectors. We develop two new frameworks to address a gap in current modelling frameworks, focusing on the means and tempo of an AML attack against MARL, and identify knowledge gaps and future avenues of research.