Journal
2022 IEEE INTERNATIONAL CONFERENCE ON CYBER SECURITY AND RESILIENCE (IEEE CSR)
Volume -, Issue -, Pages 16-21Publisher
IEEE
DOI: 10.1109/CSR54599.2022.9850343
Keywords
Multi-Agent Reinforcement Learning; adversarial attacks; LSTM; anomaly detection
Categories
Funding
- National Science Foundation (NSF) [2105007]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [2105007] Funding Source: National Science Foundation
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available