Open Access

ARTICLE

A Lightweight Time-Indexed Secure Communication Framework with Intrusion Detection Modeling for Resource-Constrained UAV Swarm Networks

Li-Woei Chen¹, Kun-Lin Tsai^2,*, Fang-Yie Leu³, Chao-Tung Yang^3,4,5, Wei-Zong Liang²

1 Department of Computer and Information Sciences, Chinese Military Academy, Kaohsiung, Taiwan
2 Department of Electrical Engineering, Tunghai University, Taichung, Taiwan
3 Department of Computer Science, Tunghai University, Taichung, Taiwan
4 Research Center for Smart Sustainable Circular Economy, Tunghai University, Taichung, Taiwan
5 Department of Medical Research, Kuang Tien General Hospital, Taichung, Taiwan

* Corresponding Author: Kun-Lin Tsai. Email:

(This article belongs to the Special Issue: Advanced Security and Privacy for Future Mobile Internet and Convergence Applications: A Computer Modeling Approach)

Computer Modeling in Engineering & Sciences 2026, 148(1), 51 https://doi.org/10.32604/cmes.2026.083880

Received 12 April 2026; Accepted 11 June 2026; Issue published 27 July 2026

Abstract

Unmanned aerial vehicle (UAV) swarm networks are increasingly deployed in surveillance, disaster response, and intelligent transportation systems, where secure and efficient communication is critical under resource-constrained environments. However, conventional public-key-based security mechanisms introduce excessive computational overhead, while standalone intrusion detection systems are insufficient to defend against dynamic and multi-vector attacks in swarm networks. To address these challenges, in this paper, a lightweight time-indexed secure communication framework with intrusion detection modeling (TSCID) is proposed for resource-constrained UAV swarm networks. The proposed TSCID integrates a time-indexed session key derivation mechanism with lightweight authenticated encryption to ensure confidentiality, integrity, replay resistance, and session-key isolation with low computational cost. A security and communication-overhead analysis under standard symmetric-key cryptographic assumptions is conducted to evaluate the practicality and lightweight characteristics of the proposed framework. To enhance resilience against network-level attacks, an intrusion detection module based on deep neural networks is incorporated and optimized through structured pruning, enabling real-time anomaly detection on edge-class UAV devices. Experimental results demonstrate that TSCID reduces communication latency by up to 35% and energy consumption by nearly 30% compared with conventional public-key-based security mechanisms, while the lightweight intrusion detection model achieves over 92% detection accuracy with less than 4% false positives. Analytical and experimental results confirm that the proposed framework provides an efficient and secure solution for real-time UAV swarm communication under strict resource constraints.

---

Keywords

---