Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising

06/14/2022
by   Zikang Xiong, et al.
15

Neural network policies trained using Deep Reinforcement Learning (DRL) are well-known to be susceptible to adversarial attacks. In this paper, we consider attacks manifesting as perturbations in the observation space managed by the external environment. These attacks have been shown to downgrade policy performance significantly. We focus our attention on well-trained deterministic and stochastic neural network policies in the context of continuous control benchmarks subject to four well-studied observation space adversarial attacks. To defend against these attacks, we propose a novel defense strategy using a detect-and-denoise schema. Unlike previous adversarial training approaches that sample data in adversarial scenarios, our solution does not require sampling data in an environment under attack, thereby greatly reducing risk during training. Detailed experimental results show that our technique is comparable with state-of-the-art adversarial training approaches.

READ FULL TEXT
research
05/16/2022

Attacking and Defending Deep Reinforcement Learning Policies

Recent studies have shown that deep reinforcement learning (DRL) policie...
research
11/13/2020

Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents

Advances in computing resources have resulted in the increasing complexi...
research
06/09/2023

Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions

Learning in MDPs with highly complex state representations is currently ...
research
05/29/2019

Targeted Attacks on Deep Reinforcement Learning Agents through Adversarial Observations

This paper deals with adversarial attacks on perceptions of neural netwo...
research
07/31/2019

Optimal Attacks on Reinforcement Learning Policies

Control policies, trained using the Deep Reinforcement Learning, have be...
research
06/06/2022

Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning

The danger of adversarial attacks to unprotected Uncrewed Aerial Vehicle...
research
07/21/2019

Characterizing Attacks on Deep Reinforcement Learning

Deep reinforcement learning (DRL) has achieved great success in various ...

Please sign up or login with your details

Forgot password? Click here to reset