Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control

Abstract

Deep reinforcement learning (DRL) has recently been used to perform efficient resource allocation in wireless communications. In this paper, the vulnerabilities of such DRL agents to adversarial attacks is studied. In particular, we consider multiple DRL agents that perform both dynamic channel access and power control in wireless interference channels. For these victim DRL agents, we design a jammer, which is also a DRL agent. We propose an adversarial jamming attack scheme that utilizes a listening phase and significantly degrades the users' sum rate. Subsequently, we develop an ensemble policy defense strategy against such a jamming attacker by reloading models (saved during retraining) that have minimum transition correlation.

References in corpus (9)

• Dueling Network Architectures for Deep Reinforcement Learning
• Theoretically Principled Trade-off between Robustness and Accuracy
• Deep Recurrent Q-Learning for Partially Observable MDPs
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• Adversarial Policies: Attacking Deep Reinforcement Learning
• Characterizing Attacks on Deep Reinforcement Learning
• Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
• When Wireless Security Meets Machine Learning: Motivation, Challenges, and Research Directions
• Enhancing Cross-task Transferability of Adversarial Examples with Dispersion Reduction