期刊
出版社
IEEE
DOI: 10.1109/CSR54599.2022.9850343
关键词
Multi-Agent Reinforcement Learning; adversarial attacks; LSTM; anomaly detection
资金
- National Science Foundation (NSF) [2105007]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [2105007] Funding Source: National Science Foundation
This paper investigates the security vulnerability in Multi-Agent Reinforcement Learning (MARL) algorithms, focusing on compromised agent attacks, and proposes a novel detection method that outperforms existing baseline models.
Multi-Agent Reinforcement Learning (MARL) extends individual reinforcement learning to enable a team of agents to collaboratively determine the global optimal policy that maximizes the sum of their local accumulated rewards. It has been recently deployed in multiple application domains such as edge computing, wireless networks, and Cyber-Physical Systems. Nonetheless, the security of MARL and its potential exposure to cyberattacks have not yet been fully investigated. This paper examines one of the most serious vulnerabilities in MARL algorithms: the compromised agent. This newly-engineered adversarial vulnerability is exploited when a malicious user compromises an agent to directly control its actions, and subsequently pushes its cooperative agents to act off-policy. We present a novel stacked-LSTM ensemble approach to detect such an attack. The results show that our anomalous behavior detection system significantly outperforms five baselines from the liteIrnadteuxre.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据