Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
Wu Yichao, Wang Yirui, Ding Panpan, Wang Hailong, Zhu Bingqian, Liu Chun
TL;DR
This survey analyzes the security of deep reinforcement learning (DRL) by introducing a taxonomy of adversarial attacks organized by perturbation type and attack target, and by systematically reviewing robustness-enhancing defenses. It covers attacks that perturb the state, reward, action, and model spaces, and discusses defensive strategies including adversarial and competitive training, robust learning, detection, and defensive distillation. The authors identify key challenges such as generalization, computational complexity, scalability, and explainability, and propose future directions toward adaptive, transferable, and hardware-aware defenses. The work aims to guide researchers and practitioners in designing DRL systems that remain reliable and safe in adversarial and dynamic environments.
Abstract
With the wide application of deep reinforcement learning (DRL) techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research. Especially in the face of adversarial attacks, DRL may suffer serious performance degradation or even make potentially dangerous decisions, so it is crucial to ensure their stability in security-sensitive scenarios. In this paper, we first introduce the basic framework of DRL and analyze the main security challenges faced in complex and changing environments. In addition, this paper proposes an adversarial attack classification framework based on perturbation type and attack target and reviews the mainstream adversarial attack methods against DRL in detail, including various attack methods such as perturbation state space, action space, reward function and model space. To effectively counter the attacks, this paper systematically summarizes various current robustness training strategies, including adversarial training, competitive training, robust learning, adversarial detection, defense distillation and other related defense techniques, we also discuss the advantages and shortcomings of these methods in improving the robustness of DRL. Finally, this paper looks into the future research direction of DRL in adversarial environments, emphasizing the research needs in terms of improving generalization, reducing computational complexity, and enhancing scalability and explainability, aiming to provide valuable references and directions for researchers.