Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
It tackles security vulnerabilities in DRL for real-world critical systems, but it is incremental as it is a survey paper.
This paper addresses the problem of adversarial attacks on Deep Reinforcement Learning (DRL) systems, which hinder their use in critical applications like smart grids and autonomous vehicles, by providing a comprehensive survey of emerging attacks and potential countermeasures.
Deep Reinforcement Learning (DRL) has numerous applications in the real world thanks to its outstanding ability in quickly adapting to the surrounding environments. Despite its great advantages, DRL is susceptible to adversarial attacks, which precludes its use in real-life critical systems and applications (e.g., smart grids, traffic controls, and autonomous vehicles) unless its vulnerabilities are addressed and mitigated. Thus, this paper provides a comprehensive survey that discusses emerging attacks in DRL-based systems and the potential countermeasures to defend against these attacks. We first cover some fundamental backgrounds about DRL and present emerging adversarial attacks on machine learning techniques. We then investigate more details of the vulnerabilities that the adversary can exploit to attack DRL along with the state-of-the-art countermeasures to prevent such attacks. Finally, we highlight open issues and research challenges for developing solutions to deal with attacks for DRL-based intelligent systems.