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

Authors: Maxwell Standen, Junae Kim, Claudia Szabo
Published: 2023-01-11

Source: https://arxiv.org/abs/2301.04299

PDF: https://arxiv.org/pdf/2301.04299

Labels Predicted by AI

敵対的攻撃手法 DNN IP保護手法 構造的攻撃

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

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.