Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
ACM Computing Surveys · 31.05.2025 · 57 (5) · 1-35
DOI: 10.1145/3708320 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 24.01.2025. Verfasst von Maxwell Standen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 159 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Standen, M., Kim, J., & Szabo, C. (2025). Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning. ACM Computing Surveys, 57(5), 1-35. https://doi.org/10.1145/3708320
Vancouver
Standen M, Kim J, Szabo C. Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning. ACM Computing Surveys. 2025;57(5):1-35. doi:10.1145/3708320
BibTeX
@article{Standen2025,
author = {Standen, Maxwell and Kim, Junae and Szabo, Claudia},
title = {Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {5},
pages = {1--35},
doi = {10.1145/3708320}
}
EUVIMED