Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control

TL;DR

This paper investigates the vulnerabilities of deep reinforcement learning agents in wireless resource management to adversarial jamming attacks and proposes a defense strategy using ensemble policies to mitigate such attacks.

Contribution

It introduces an adversarial jamming attack scheme against DRL-based channel access and power control and proposes an ensemble policy defense mechanism.

Findings

The jamming significantly reduces the users' sum rate.

Ensemble policy defense improves robustness against adversarial attacks.

The proposed scheme effectively degrades and then mitigates attack impacts.

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.