Smart Shield: Prevent Aerial Eavesdropping via Cooperative Intelligent Jamming Based on Multi-Agent Reinforcement Learning

The spotlight on autonomous aerial vehicles (AAVs) is to enhance wireless communications while ignoring the potential risk of AAVs acting as adversaries. Due to their mobility and flexibility, AAV eavesdroppers pose an immeasurable threat to legitimate wireless transmissions. However, the existing fixed jamming scheme without cooperation cannot counter the flexible and dynamic AAV eavesdropping. In this article, a cooperative intelligent jamming scheme is proposed, authorizing ground jammers (GJs) to interfere with AAV eavesdroppers, generating specific jamming shields between AAV eavesdroppers and legitimate users. Toward this end, we formulate a secrecy capacity maximization problem and model the problem as a decentralized partially observable Markov decision process (Dec-POMDP). To address the challenge of the huge state space and action space with network dynamics, we leverage a deep reinforcement learning (DRL) algorithm with a dueling network and double-Q learning (i.e., dueling double deep Q-network) to train policy networks. Then, we propose a multi-agent mixing network framework (QMIX)-based collaborative jamming algorithm to enable GJs to independently make decisions without sharing local information. Additionally, we perform extensive simulations to validate the superiority of our proposed scheme and present useful insights into practical implementation by elucidating the relationship between the deployment settings of GJs and the instantaneous secrecy capacity.

I. Introduction

With advancements in intelligent control, precision guidance, and energy supply technologies [1], Autonomous Aerial Vehicles (AAVs) have become invaluable in various fields, including environmental monitoring, military operations, and civilian applications. Their ability to perform rapid deployment and flexible networking makes them powerful assets in wireless communications [2], [3]. However, the increasing number of deployed AAVs, if controlled or disguised by adversaries, poses significant and unpredictable threats to wireless communication security [4]. Due to their high mobility and flexibility, AAVs can hover at strategic positions to intercept confidential data on wireless channels, acting as eavesdroppers. This threat is particularly critical in sensitive environments such as military operations, where AAV eavesdropping can compromise mission-critical information, and in civilian sectors, where it can lead to breaches of personal and corporate data. Moreover, AAV eavesdroppers benefit from high eavesdropping channel quality due to dominant line-of-sight (LoS) gain, enhancing their interception capabilities. Recent research has demonstrated the potential risks and technical challenges associated with AAV eavesdropping, emphasizing the need for robust security measures [5], [6]. Therefore, developing effective countermeasures against AAV eavesdroppers is both imperative and vital to protect the integrity of systems for wireless communication across various domains.