Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
2-2020
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 domainagnostic 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-theart methods.
Discipline
Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
Proceedings of 34rd AAAI Conference on Artificial Intelligence (AAAI), New York, 2020 February 7-12
First Page
5883
Last Page
5891
ISBN
9781577358350
Publisher
AAAI
City or Country
New York, USA
Citation
SUN, Jianwen; ZHANG, Tianwei; XIE, Xiaofei; MA, Lei; ZHENG, Yan; CHEN, Kangjie; and LIU, Yang.
Stealthy and efficient adversarial attacks against deep reinforcement learning. (2020). Proceedings of 34rd AAAI Conference on Artificial Intelligence (AAAI), New York, 2020 February 7-12. 5883-5891.
Available at: https://ink.library.smu.edu.sg/sis_research/7116
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.