6G Sensing Security Distributed Game-Theoretic RL for Urban Beamforming and Attacker Detection

Jul 16, 2026

Upload by Riley

Next-generation networks extend beyond communication to sense the environment through integrated sensing and communication (ISAC), reusing wireless infrastructure for both data transmission and environmental observation. This work targets active attacker detection in an urban scenario where the attacker manipulates beamforming directions to increase interference and misdirect the transmitter’s main lobe. A game-theoretic interaction between legitimate users and the attacker is formulated and embedded in a reinforcement learning framework. Simulations show effective security against dynamic 6G ISAC threats.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

Introduction

Integrated sensing and communication (ISAC)

Security challenges and physical-layer protection

Incomplete-information games and RL

System model and simulation setup

3GPP TR 38.901 urban micro scenario

Network geometry and link parameters

6G Sensing Security: Distributed Game-Theoretic RL for Urban Beamforming and Attacker Detection Parmida Geranmayeh∗ and Onur G¨unl¨u∗† ∗ Lehrstuhl f¨ur Nachrichtentechnik, Technische Universitt Dortmund, Germany {parmida.geranmayeh, [onur.guenlue](onur.guenlue}@tu-dortmund.de)[}](onur.guenlue}@tu-dortmund.de)[@tu-dortmund.de](onur.guenlue}@tu-dortmund.de) †Information Theory and Security Laboratory (ITSL), Linkping University, Sweden arXiv :2607 .06 1 15v 1 [ cs .IT] 7 Jul 2026 Abstract—In next-generation networks, communication systems will no longer be limited to data transmission and will be expected to acquire awareness of the surrounding environment. This leads to the concept of integrated sensing and communication (ISAC), where the same wireless infrastructure is used for both communication and environmental sensing. Thus, ISAC enables the system to transmit information efficiently and observe and interpret channel variations and user behavior. Motivated by this capability, this work focuses on detecting an active attacker inan urban environment scenario, where the attacker intentionally manipulates beamforming directions to increase interference and mislead the transmitter into allocating the main lobe of beam toward itself instead of legitimate users. We apply game-theoretic approaches to model the interaction between legitimate users and the attacker, and integrate the resulting utility-based formulation into a reinforcement learning (RL) framework. Simulation results demonstrate that the proposed method effectively addresses security challenges in dynamic 6G ISAC systems. Index Terms—Beamforming, game theory, sensing security, integrated sensing and communication, reinforcement learning. I. INTRODUCTION Integrated sensing and communication (ISAC) is seen asa promising technology for future wireless networks [1], [2] investigated from different perspectives, such as waveform design, resource allocation, beamforming, and system performance analysis [3], [4], [5] . Combining sensing and communication functions reduces spectrum congestion between radar and communication systems, while improving spectrum efficiency and decreasing hardware cost [6] . Recent research has further highlighted the importance of securing ISAC systems to increase trust in the ISAC-based system outcomes [7], [8] . However, interference management remains a critical challenge. Beamforming is an effective approach for mitigating interference and improving system performance [9] and enhances signal quality, increases coverage, and mitigates cochannel interference. These improvements result in enhanced data rates, reduced latency, and overall increased network capacity. [10] . However, ISAC introduces additional security challenges [2] . Consequently, secure designs, particularly in the area of physical-layer security, have become important. Recent work aims to enhance communication security and sensing performance [2], [11] . Network security research based on incomplete-information games has also achieved considerable progress. For instance, in [12] an incomplete-information Markov game model incorporating moving attack and moving detection surfaces is proposed. This framework jointly considers defense effectiveness and operational cost, while selecting optimal defense strategies under realistic network conditions. In [13], a multistage Markov signaling game approach for moving target defense is considered, where optimal defense strategies are determined despite uncertain prior information. Moreover,[14] highlights the importance of adaptive decision-making strategies in incomplete-information games. Additionally, learningbased frameworks have also been extended to ISAC systems to jointly address security, sensing, and communication performance under dynamic and uncertain environments. Reinforcement learning (RL) provides an effective framework in which agents continuously refine their strategies through interactions with the en

FAQs

What attacker behavior does the paper consider in urban ISAC beamforming?

The attacker intentionally manipulates beamforming directions to increase interference and mislead the transmitter into steering the main lobe toward the attacker instead of legitimate users.

How are game-theoretic models integrated with reinforcement learning in the proposed method?

The interaction between legitimate users and the attacker is modeled using game-theoretic, utility-based formulations, and this formulation is incorporated into a reinforcement learning framework so agents learn appropriate strategies under uncertainty.

What simulation setting is used to evaluate the approach?

Simulations are based on the 3GPP TR 38.901 Urban Micro (UMi) scenario, using 28 GHz carrier frequency in the FR2 mmWave band with 400 MHz bandwidth, and a network with two transmit base stations and four receivers.

Jul 16, 2026

Upload by Riley