PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning
This work addresses security vulnerabilities in Safe RL, a critical area for safety-critical applications, though it is incremental as it applies existing backdoor attack concepts to a new domain.
The paper identifies that Safe Reinforcement Learning (Safe RL) is vulnerable to backdoor attacks, which can manipulate agents into performing unsafe actions, and introduces the PNAct framework as the first attack method in this field, demonstrating its effectiveness through experiments.
Reinforcement Learning (RL) is widely used in tasks where agents interact with an environment to maximize rewards. Building on this foundation, Safe Reinforcement Learning (Safe RL) incorporates a cost metric alongside the reward metric, ensuring that agents adhere to safety constraints during decision-making. In this paper, we identify that Safe RL is vulnerable to backdoor attacks, which can manipulate agents into performing unsafe actions. First, we introduce the relevant concepts and evaluation metrics for backdoor attacks in Safe RL. It is the first attack framework in the Safe RL field that involves both Positive and Negative Action sample (PNAct) is to implant backdoors, where positive action samples provide reference actions and negative action samples indicate actions to be avoided. We theoretically point out the properties of PNAct and design an attack algorithm. Finally, we conduct experiments to evaluate the effectiveness of our proposed backdoor attack framework, evaluating it with the established metrics. This paper highlights the potential risks associated with Safe RL and underscores the feasibility of such attacks. Our code and supplementary material are available at https://github.com/azure-123/PNAct.