Stealthy and efficient adversarial attacks against deep reinforcement learning

Jianwen Sun, Tianwei Zhang, Xiaofei Xie, Lei Ma, Yan Zheng, Kangjie Chen, Yang Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed. However, the possibility and feasibility of such attacks against Deep Reinforcement Learning (DRL) are less explored. As DRL has achieved great success in various complex tasks, designing effective adversarial attacks is an indispensable prerequisite towards building robust DRL algorithms. In this paper, we introduce two novel adversarial attack techniques to stealthily and efficiently attack the DRL agents. These two techniques enable an adversary to inject adversarial samples in a minimal set of critical moments while causing the most severe damage to the agent. The first technique is the critical point attack: the adversary builds a model to predict the future environmental states and agent's actions, assesses the damage of each possible attack strategy, and selects the optimal one. The second technique is the antagonist attack: the adversary automatically learns a domain-agnostic model to discover the critical moments of attacking the agent in an episode. Experimental results demonstrate the effectiveness of our techniques. Specifically, to successfully attack the DRL agent, our critical point technique only requires 1 (TORCS) or 2 (Atari Pong and Breakout) steps, and the antagonist technique needs fewer than 5 steps (4 Mujoco tasks), which are significant improvements over state-of-the-art methods.

Original languageEnglish
Title of host publicationAAAI 2020 - 34th AAAI Conference on Artificial Intelligence
PublisherAAAI Press
Pages5883-5891
Number of pages9
ISBN (Electronic)9781577358350
Publication statusPublished - 2020
Event34th AAAI Conference on Artificial Intelligence, AAAI 2020 - New York, United States
Duration: Feb 7 2020Feb 12 2020

Publication series

NameAAAI 2020 - 34th AAAI Conference on Artificial Intelligence

Conference

Conference34th AAAI Conference on Artificial Intelligence, AAAI 2020
Country/TerritoryUnited States
CityNew York
Period2/7/202/12/20

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Stealthy and efficient adversarial attacks against deep reinforcement learning'. Together they form a unique fingerprint.

Cite this