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

• 来源期刊: 网络空间安全科学与技术（英文版）
• 关键词: Reinforcement learning Artificial intelligence Security Adversarial attack Adversarial example Defense
• 年，卷（期）: 2019,（1）
• 页码范围: 12-33
• 页数: 22页
• 语种: 中文

摘要

Reinforcement learning is a core technology for modern artificial intelligence,and it has become a workhorse for Al applications ranging from Atrai Game to Connected and Automoted Vehicle System (CAV).Therefore,a reliable RL system is the foundation for the security critical applications in Al,which has attracted a concern that is more critical than ever.However,recent studies discover that the interesting attack mode adversarialattack 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 Al security.Moreover,we give briefly introduction on the most representative defense technologies against existing adversarial attacks.