Adversarial attack and defense in reinforcement learning-from AI security view

Cybersecurity

Jiqiang Liu¹  Zhen Han¹  Tong Chen¹  Wenjia Niu¹  Yingxiao Xiang¹  Endong Tong¹ 

[1] Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University;

关键词: Reinforcement learning;    Artificial intelligence;    Security;    Adversarial attack;    Adversarial example;    Defense;   

DOI  :  10.1186/s42400-019-0027-x

来源: DOAJ

【 摘 要 】

Abstract Reinforcement learning is a core technology for modern artificial intelligence, and it has become a workhorse for AI applications ranging from Atrai Game to Connected and Automated Vehicle System (CAV). Therefore, a reliable RL system is the foundation for the security critical applications in AI, which has attracted a concern that is more critical than ever. However, recent studies discover that the interesting attack mode adversarial attack also be effective when targeting neural network policies in the context of reinforcement learning, which has inspired innovative researches in this direction. Hence, in this paper, we give the very first attempt to conduct a comprehensive survey on adversarial attacks in reinforcement learning under AI security. Moreover, we give briefly introduction on the most representative defense technologies against existing adversarial attacks.

【 授权许可】

Unknown