Trusted Routing for Blockchain-Empowered UAV Networks via Multi-Agent Deep Reinforcement Learning

Oct 22, 2026

Upload by asda1da

Trusted routing for blockchain-empowered UAV networks addresses the vulnerability of routing under distributed topology, high mobility, and malicious node attacks. The paper models time-varying routing as an integer linear programming problem to minimize total delay, then introduces a blockchain-based trust management mechanism to dynamically evaluate trust and detect low-trust UAVs. It also proposes a consensus UAV update and a decentralized partially observable Markov decision process with a multi-agent double deep Q-network to reduce end-to-end delay.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Routing security under malicious UAVs

Delay as a key QoS metric

Limitations of traditional routing algorithms

Trusted Routing for Blockchain-Empowered UAV Networks via Multi-Agent Deep Reinforcement Learning Ziye Jia, Member, IEEE, Sijie He, Qiuming Zhu, Senior Member, IEEE, Wei Wang, Member, IEEE, Qihui Wu, Fellow, IEEE, and Zhu Han, Fellow, IEEE arXiv :2508 .00938v1 [ ee ss . SY] 31 Jul 2025 Abstract—Due to the high flexibility and versatility, unmanned aerial vehicles (UAVs) are leveraged in various fields including surveillance and disaster rescue. However, in UAV networks, routing is vulnerable to malicious damage due to distributed topologies and high dynamics. Hence, ensuring the routing security of UAV networks is challenging. In this paper, we characterize the routing process in a time-varying UAV network with malicious nodes. Specifically, we formulate the routing problem to minimize the total delay, which is an integer linear programming and intractable to solve. Then, to tackle the network security issue, a blockchain-based trust management mechanism (BTMM) is designed to dynamically evaluate trust values and identify lowtrust UAVs. To improve traditional practical Byzantine fault tolerance algorithms in the blockchain, we propose a consensus UAV update mechanism. Besides, considering the local observability, the routing problem is reformulated into a decentralized partially observable Markov decision process. Further, a multi-agent double deep Q-network based routing algorithm is designed to minimize the total delay. Finally, simulations are conducted with attacked UAVs and numerical results show that the delay of the proposed mechanism decreases by 13.39%, 12.74%, and 16.6% than multiagent proximal policy optimal algorithms, multi-agent deep Qnetwork algorithms, and methods without BTMM, respectively. Index Terms—UAV network, trusted routing, blockchain, multiagent deep reinforcement learning, Byzantine fault tolerance. I. INTRODUCTION ASnaeteoyrk component of the space-air-ground integrated in the six generation communication techniques, unmanned aerial vehicles (UAVs) are rapidly developed and widely applied to multiple tasks, such as disaster rescue and real-time monitoring [1], [2] . In these applications, UAVs can serve as aerial base stations for data collection and transmission, providing low-cost, flexible, and versatile services [3] . Besides, UAV networking can cooperatively accomplish complex tasks, in which routing is a significant issue for optimizing the Ziye Jia is with the College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China, and also with the State Key Laboratory of Integrated Service Networks, Xidian University, Xi’an Shaanxi 710071, China (e-mail: [jiaziye@nuaa.edu.cn](jiaziye@nuaa.edu.cn)). Sijie He, Qiuming Zhu, Wei Wang, and Qihui Wu are with the College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China (e-mail: [sx2304109@nuaa.edu.cn](sx2304109@nuaa.edu.cn); [zhuqiuming@nuaa.edu.cn](zhuqiuming@nuaa.edu.cn); [wei_wang@nuaa.edu.cn](wei_wang@nuaa.edu.cn); [wuqihui@nuaa.edu.cn](wuqihui@nuaa.edu.cn)). Zhu Han is with the University of Houston, Houston, TX 77004 USA, and also with the Department of Computer Science and Engineering, Kyung Hee University, Seoul 446-701, South Korea (e-mail: [hanzhu22@gmail.com](hanzhu22@gmail.com)). data transmission [4]–[6] . Moreover, since UAV networks are characterized by the complex application environment, high dynamic and distributed topology, they are vulnerable to malicious attacks [3] . When there exist malicious UAVs, the hostile activities can lead to the degradation of routing performances. Therefore, it is necessary to evaluate the behaviors and manage the malicious UAVs. There exist a couple of works focusing on building the node trust table by a single-node based centralized manager, which is not resilient to fault tolerance and can be easily tampered with [7] . Hence, to improve the routing sec

FAQs

What routing problem is formulated in the paper?

The routing problem is formulated to minimize the total end-to-end delay in a time-varying UAV network with malicious nodes.

How does the proposed method identify low-trust UAVs?

It designs a blockchain-based trust management mechanism that dynamically evaluates trust values and identifies low-trust UAVs.

What algorithm is used to solve the decentralized routing under partial observability?

The paper reformulates routing into a decentralized partially observable Markov decision process and uses a multi-agent double deep Q-network routing algorithm.

Oct 22, 2026

Upload by asda1da