Adversarial reinforcement learning in dynamic channel access and power control

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publication2021 IEEE Wireless Communications and Networking Conference, WCNC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728195056
DOIs
StatePublished - 2021
Event2021 IEEE Wireless Communications and Networking Conference, WCNC 2021 - Nanjing, China
Duration: Mar 29 2021Apr 1 2021

Publication series

NameIEEE Wireless Communications and Networking Conference, WCNC
Volume2021-March
ISSN (Print)1525-3511

Conference

Conference2021 IEEE Wireless Communications and Networking Conference, WCNC 2021
Country/TerritoryChina
CityNanjing
Period3/29/214/1/21

Keywords

  • Adversarial policies
  • Deep reinforcement learning
  • Defense strategies
  • Dynamic channel access
  • Jamming attacks

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Adversarial reinforcement learning in dynamic channel access and power control'. Together they form a unique fingerprint.

Cite this