Leveraging Q-learning For Proactive Security Against Adversarial Band Jamming In Wireless Networks

Abstract

Wireless Networks Are Being Used In Several Applications These Days Such As Large Scale Industries, Chemical Plants, Underground Mines, Disaster Management, Military And Defense Etc. However, Due To The Large Scale Of The Network And Wireless Data Transfer, The Data Transmission Is Often Prone To Attacks. In This Context, Physical Layer Security (PLS) Has Emerged As An Attractive Solution For Securing Wireless Transmissions By Exploiting The Wireless Channel Characteristics.This Work Presents A Deep Reinforcement Learning Based Approach For Frequency Hopping Mechanism To Ensure Security To Wireless Sensor Networks. The Evaluation Parameters Chosen Are Average Reward, BER And Outage Probability. It Can Be Observed From The Results That As The Spreading Factor Increases, The BER Also Increase Showing A Compromise Between Security And Errors. It Has Been Shown That The Proposed System Achieves Lower BER And Outage Probability Compared To Previously Existing Techniques.

Keywords