Stealthy data poisoning attack method on offline reinforcement learning in unmanned systems
Year: 2024
Type: article
Abstract: Aiming at the limitations in effectiveness and stealth of existing offline reinforcement learning(RL) data poisoning attacks, a critical time-step dynamic poisoning attack was proposed, perturbing important samples to achieve efficient and covert attacks. Temporal difference errors, identified through theoretical analysis as crucial for model learning, were used to guide poisoning target selection. A bi-objective optimization approach was introduced to minimize perturbation magnitude while maximizing the negative impact on performance. Experimental results show that with only a 1% poisoning rate, the method reduces agent performance by 84%, revealing the sensitivity and vulnerability of offline RL models in unmanned systems.
Authors: ZHOU Xue, MAN Dapeng, XU Chen, LYU Jiguang, ZENG Fanyi, GAO Chaoyang, YANG Wu
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7062043299
FWCI:
Cites:
Cited by:
Related to: