Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
Top Cited Papers
Open Access
- 24 January 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (5) , 1-35
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.Keywords
All Related Versions
This publication has 71 references indexed in Scilit:
- Deep reinforcement learning based control for Autonomous Vehicles in CARLAMultimedia Tools and Applications, 2022
- Deep Adversarial Reinforcement Learning With Noise Compensation by AutoencoderIEEE Access, 2021
- Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement LearningIEEE Transactions on Neural Networks and Learning Systems, 2021
- Regularisation of neural networks by enforcing Lipschitz continuityMachine Learning, 2020
- Adversarial Attacks and Defenses in Deep LearningEngineering, 2020
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- One Pixel Attack for Fooling Deep Neural NetworksIEEE Transactions on Evolutionary Computation, 2019
- Deep Reinforcement Learning: A Brief SurveyIEEE Signal Processing Magazine, 2017
- Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks2017
- Systematic literature reviews in software engineering – A systematic literature reviewInformation and Software Technology, 2009