AI- Based UAV with Fuzzy Logic Algorithm using Wormhole Attack Detection in Wireless Sensor Networks

Abstract

Wireless Sensor Networks (WSNs) play a vital role in modern communication systems but remain highly vulnerable to sophisticated security threats—particularly wormhole attacks. These attacks exploit low-latency links between compromised nodes, disrupting routing protocols and often bypassing conventional cryptographic defenses. To address this challenge, this study proposes an AI-based Unmanned Aerial Vehicle (UAV) system integrated with a fuzzy logic algorithm to enhance the detection and mitigation of wormhole attacks in WSNs. The UAV acts as a mobile monitoring agent, dynamically analyzing communication patterns and network behaviors. Fuzzy logic enables the system to make intelligent decisions based on uncertain or imprecise inputs such as signal strength, hop count deviation, and packet delay. By incorporating energy-aware fuzzy clustering, the UAV optimizes its flight and monitoring tasks, extending network lifetime and improving detection accuracy. This research not only compares existing wormhole detection techniques but also introduces a novel, adaptive, and energy-efficient approach using AI and UAV technology to safeguard WSNs from one of their most dangerous attack vectors.

Introduction

Wireless Sensor Networks (WSNs) are increasingly vulnerable to Distributed Denial-of-Service (DDoS) attacks, notably wormhole attacks, which involve malicious nodes creating covert tunnels that disrupt network routing. Wormhole attacks are challenging to detect because they manipulate packet routes without altering the visible network structure. These attacks can be classified as open, half-open, or closed wormholes, depending on node visibility and communication methods.

WSNs, composed of low-cost, energy-efficient sensor nodes, are widely used in diverse applications like environmental monitoring, healthcare, and military operations. However, their limited resources and dynamic topologies make them susceptible to security threats including wormholes, black holes, and clone attacks.

To combat wormhole attacks, various AI and machine learning-based detection and prevention techniques have been developed. These include fuzzy logic integrated with artificial immune systems, support vector machines, artificial neural networks, deep learning with LSTM, and other classifiers such as decision trees and KNN. Such approaches enhance detection accuracy, reduce false positives, conserve energy, and improve packet delivery.

The text proposes an AI-enabled Unmanned Aerial Vehicle (UAV) routing protocol extension of AODV that discovers multiple routes and uses timing metrics (round-trip time per hop) to identify suspicious routes indicative of wormholes. Suspicious nodes are blacklisted and removed from routing tables to prevent attack recurrence. The system uses fuzzy logic clustering with UAV mobility to dynamically monitor the network and detect anomalies.

Simulation results demonstrate that this AI-based UAV method outperforms existing protocols in throughput, end-to-end delay, packet delivery ratio, and energy efficiency, especially in high-density networks. The approach maintains high detection accuracy (~99.45%) with lower overhead and improved network resilience compared to other state-of-the-art methods.

The document concludes that AI and ML techniques, particularly those incorporating weighted clustering and multiple classifiers, offer optimal solutions to the challenges faced by WSN security, including energy consumption, detection accuracy, and scalability.

Conclusion

A wide range of existing schemes aimed at both detecting and mitigating wormhole attacks. These include approaches based on artificial intelligence (AI) and machine learning (ML), neighbor discovery and path selection, statistical analysis, AODV protocol, round-trip time (RTT) and hop count, as well as cloud computing and mobile agent-based techniques. A Systematic Literature Review (SLR) has been conducted to critically and comparatively analyze these methods.Each scheme was evaluated across several key performance metrics, including detection accuracy, network lifetime, energy efficiency, algorithmic complexity, packet delivery ratio (PDR), packet loss ratio (PLR), and latency. Through this review, significant gaps in the existing literature were identified, highlighting areas for future research in both the detection and prevention of wormhole attacks.Recent studies demonstrate that AI-based approaches, particularly those leveraging machine learning techniques, have shown notably high detection accuracy, outperforming many traditional methods. The comparative analysis confirms that AI- and ML-driven solutions offer more robust, scalable, and efficient performance compared to conventional state-of-the-art techniques.

References

[1] Murty, M. V. D. S. K., & Rajamani, Dr. L. Neighbour NodeRatio AODV (NNR-AODV) Routing Protocol for Wormhole Attack Detection in MANETs. In International Journal of Emerging Scienceand Engineering, PP: 1-9 | Volume-11 Issue-4, March 2023 | Retrieval Number: 100.1/ijese.D25470311423 | DOI: 10.35940/ijese.D2547.0311423 [2] Luo, X.; Chen, Y.; Li, M.; Luo, Q.; Xue, K.; Liu, S.; Chen, L. CREDND: A novel secure neighbor discovery algorithm for wormhole attack. IEEE Access 2019, 7, 18194–18205. [CrossRef] [3] Alenezi, F.A.; Song, S.; Choi, B.Y. SWANS: SDN-based Wormhole Analysis using the Neighbor Similarity for a Mobile ad hoc network (MANET). In Proceedings of the 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), Bordeaux, France, 17–21 May 2021; pp. 653–657. [4] Vo, T.T.; Luong, N.T.; Hoang, D. MLAMAN: A novel multi-level authentication model and protocol for preventing wormhole attacks in mobile ad hoc networks. Wirel. Netw. 2019, 25, 4115–4132. [CrossRef] [5] Bai, S.; Liu, Y.; Li, Z.; Bai, X. Detecting wormhole attacks in 3D wireless ad hoc networks via 3D forbidden substructures. Comput. Netw. 2019, 150, 190–200. [CrossRef] [6] Patel, M.; Aggarwal, A.; Chaubey, N. Detection of Wormhole Attack in Static Wireless Sensor Networks. In Advances in Computer Communication and Computational Sciences; Springer: Singapore, 2019; Volume 760, pp. 463–471. [CrossRef] [7] Aliady, W.A.; Al-Ahmadi, S.A. Energy preserving secure measure against wormhole attack in wireless sensor networks. IEEE Access 2019, 7, 84132–84141. [CrossRef] [8] Zardari, Z.A.; Memon, K.A.; Shah, R.A.; Dehraj, S.; Ahmed, I. A lightweight technique for detection and prevention of wormhole attacks in MANET. EAI Endorsed Trans. Scalable Inf. Syst. 2021, 8, e2. [CrossRef] [9] Roy, A.K.; Khan, A.K. RTT-based wormhole detection for wireless mesh networks. Int. J. Inf. Technol. 2020, 12, 1–8. [CrossRef] [10] Karthigadevi, K.; Balamurali, S.; Venkatesulu, M. Wormhole attack detection and prevention using EIGRP protocol based on round trip time. J. Cyber Secure. Mobil. 2018, 7, 215–228. [CrossRef] [11] Kori, S.; Krishnamurthy, G.N.; Sidnal, N. Distributed Wormhole Attack Mitigation Technique in WSNs. Int. J. Comput. Netw. Inf. Secure 2019, 11, 20–27. [CrossRef] [12] Adil, M.; Almaiah, M.A.; Omar Alsayed, A.; Almomani, O. An anonymous channel categorization scheme of edge nodes to detect jamming attacks in wireless sensor networks. Sensors 2020, 20, 2311. [CrossRef] [PubMed] [13] Sampoornam, K.P.; Saranya, S.; Mohanapriya, G.K.; Devi, P.S.; Dhaarani, S. Analysis of LEACH Routing Protocol in Wireless Sensor Network with Wormhole Attack. In Proceedings of the 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India, 4–6 February 2021; pp. 147–152. [14] Numan, M.; Subhan, F.; Khan, W.Z.; Hakak, S.; Haider, S.; Reddy, G.T.; Alazab, M. A systematic review on clone node detection in static wireless sensor networks. IEEE Access 2020, 8, 65450–65461. [CrossRef] [15] Kandris, D.; Nakas, C.; Vomvas, D.; Koulouras, G. Applications of wireless sensor networks: An up-to-date survey. Appl. Syst. Innov. 2020, 3, 14. [CrossRef] [16] Premkumar, M.; Sundararajan, T.V.P. DLDM: Deep learning-based defense mechanism for denial of service attacks in wireless sensor networks. Microprocess. Microsyst. 2020, 79, 103278. [CrossRef] [17] Yousefpoor, M.S.; Yousefpoor, E.; Barati, H.; Barati, A.; Movaghar, A.; Hosseinzadeh, M. Secure data aggregation methods and countermeasures against various attacks in wireless sensor networks: A comprehensive review. J. Netw. Comput. Appl. 2021, 190, 103118. [CrossRef] [18] Ahutu, O.R.; El-Ocla, H. Centralized routing protocol for detecting wormhole attacks in wireless sensor networks. IEEE Access2020, 8, 63270–63282. [CrossRef] [19] Sankara Narayanan, S.; Murugaboopathi, G. Modified secure AODV protocol to prevent wormhole attacks in MANET. Concurr. Comput. Pract. Exp. 2020, 32, e5017. [CrossRef] [20] Alenezi, F.A.; Song, S.; Choi, B.Y. WAND: Wormhole Attack Analysis using the Neighbor Discovery for Software-defined Heterogeneous Internet of Things. In Proceedings of the 2021 IEEE International Conference on Communications Workshops (ICC Workshops), Montreal, QC, Canada, 14–23 June 2021; pp. 1–6. [21] Siddiqui, M.N.; Malik, K.R.; Malik, T.S. Performance Analysis of Blackhole and Wormhole Attack in MANET-Based IoT. In Proceedings of the 2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2), Islamabad, Pakistan, 20–21 May 2021; pp. 1–8. [22] J. P. Ntayagabiri, Y. . Bentaleb, J. Ndikumagenge, and H. . El Makhtoum,. A Comparative Analysis of Supervised Machine Learning Algorithms for IoT Attack Detection and Classification. J. Comput. Theor. Appl., vol. 2, no. 3, pp. 395–409, Feb. 2025. [23] Manar J. Gatea,Sarab M. Hameed. An Internet of Things Botnet Detection Model Using Regression Analysis and Linear Discrimination Analysis”, Iraqi Journal of Science, vol. 63, no. 10, pp. 4534–4546, Oct. 2022, doi: 10.24996/ijs.2022.63.10.36. [24] Zalak L. Thakker, Dr. Sanjay H. Buch. Effect of Feature Scaling Pre-processing Techniques on Machine Learning Algorithms to Predict Particulate Matter Concentration for Gandhinagar, Gujarat, India. International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011,Volume 11, Issue 1, pp.410-419, January-February-2024. Available at doi : https://doi.org/10.32628/IJSRST52411150

Copyright

Copyright © 2025 J. Saranya , Dr. P. Bharathisindhu . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.