Tactics of Adversarial Attack on Deep Reinforcement Learning Agents

03/08/2017
by   Yen-Chen Lin, et al.
0

We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, the adversary aims at minimizing the agent's reward by only attacking the agent at a small subset of time steps in an episode. Limiting the attack activity to this subset helps prevent detection of the attack by the agent. We propose a novel method to determine when an adversarial example should be crafted and applied. In the enchanting attack, the adversary aims at luring the agent to a designated target state. This is achieved by combining a generative model and a planning algorithm: while the generative model predicts the future states, the planning algorithm generates a preferred sequence of actions for luring the agent. A sequence of adversarial examples is then crafted to lure the agent to take the preferred sequence of actions. We apply the two tactics to the agents trained by the state-of-the-art deep reinforcement learning algorithm including DQN and A3C. In 5 Atari games, our strategically timed attack reduces as much reward as the uniform attack (i.e., attacking at every time step) does by attacking the agent 4 times less often. Our enchanting attack lures the agent toward designated target states with a more than 70 available at http://yclin.me/adversarial_attack_RL/

READ FULL TEXT

page 3

page 5

research
05/28/2019

Snooping Attacks on Deep Reinforcement Learning

Adversarial attacks have exposed a significant security vulnerability in...
research
05/14/2020

Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Adversarial attacks against conventional Deep Learning (DL) systems and ...
research
09/06/2019

Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information

Recent research on reinforcement learning has shown that trained agents ...
research
11/25/2019

Adversarial Attack with Pattern Replacement

We propose a generative model for adversarial attack. The model generate...
research
05/18/2023

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning

We propose the first black-box targeted attack against online deep reinf...
research
09/15/2022

ProAPT: Projection of APT Threats with Deep Reinforcement Learning

The highest level in the Endsley situation awareness model is called pro...
research
02/22/2022

Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach

Penetration Testing plays a critical role in evaluating the security of ...

Please sign up or login with your details

Forgot password? Click here to reset