International Journal of Wireless and Microwave Technologies (IJWMT)
IJWMT Vol. 16, No. 4, 8 Aug. 2026
Cover page and Table of Contents: PDF (size: 944KB)
FLAT: A Federated Graph Attention Network for Secure Routing and Attack Detection in MANETs
PDF (944KB), PP.378-394
Views: 0 Downloads: 0
Author(s)
Anuja Priyam
1,*
Anita Yadav
1
Index Terms
Routing, Attack Detection, MANETs, Federated Learning, Graph Attention Networks, Secure Routing
Abstract
Abstract: Mobile Ad Hoc Networks (MANETs) are autonomous wireless networks that do not rely on fixed infrastructure for communication among the mobile nodes. The mobile nodes communicate with each other with no centralized control, and routes are not established in advance. This makes MANETs vulnerable to routing attacks such as Black Hole and Sybil attacks, which divert or drop packets and thereby degrade network performance. This paper presents a novel hybrid approach combining Federated Learning (FL) and Graph Attention Network (GAT), which is termed as FLAT. GAT dynamically assigns importance to neighbouring nodes, allowing the model to capture the mobility, link instability, and heterogeneous node behaviour inherent in MANETs. FL, in turn, enables routing and attack patterns to be learned in a decentralized manner without sharing raw data. The approach was evaluated in NS-3.36 on networks ranging from 10 to 150 nodes, under Black Hole and Sybil attacks with 20% of the nodes acting maliciously, and was compared against AODV, SAODV, AOMDV, and the optimization-based Dolphin Cat Optimizer, using PDR, PLR, throughput, and end-to-end delay as evaluation metrics. It is found that the PDR of FLAT is approximately 15.1% higher than AODV and 8.2% higher than the Dolphin Cat Optimizer, while its PLR is reduced by about 77% relative to AODV, 75% relative to SAODV, and 50% relative to the Dolphin Cat Optimizer. With respect to throughput performance, FLAT shows a performance level of about 4.4, 2.8, 2.3, and 2.1 times higher than AODV, SAODV, AOMDV, and Dolphin Cat Optimizer respectively. The above findings clearly show that FLAT outperforms current techniques with regard to all measured parameters.
Cite This Paper
Anuja Priyam, Anita Yadav, "FLAT: A Federated Graph Attention Network for Secure Routing and Attack Detection in MANETs", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.4, pp. 378-394, 2026. DOI:10.5815/ijwmt.2026.04.22
Reference
[1]Salam, T., Hossen, M. "Performance analysis on homogeneous LEACH and EAMMH protocols in wireless sensor network," Wirel. Pers. Commun. 113(1), 189–222 (2020). https://doi.org/10.1007/s11277-020-07185-6
[2]Hossen, M. "DTN routing protocols on two distinct geographical regions in an opportunistic network: an analysis," Wirel. Pers. Commun. 108(2), 839–851 (2019). https://doi.org/10.1007/s11277-019-06431-w
[3]Li, X., et al. "Pooling regularized graph neural network for fMRI biomarker analysis," Med. Image Comput. Comput. Assist. Interv. 12267, 625–635 (2020). https://doi.org/10.1007/978-3-030-59728-3_61
[4]Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E. "Neural message passing for quantum chemistry," arXiv [cs.LG] (2017).
[5]Che, S., Beckmann, B.M., Reinhardt, S.K., Skadron, K. "Pannotia: understanding irregular GPGPU graph applications," In: 2013 IEEE International Symposium on Workload Characterization (IISWC), pp. 185–195 (2013). https://doi.org/10.1109/IISWC.2013.6704684
[6]Rusek, K., Suárez-Varela, J., Mestres, A., Barlet-Ros, P., Cabellos-Aparicio, A. "Unveiling the potential of graph neural networks for network modeling and optimization in SDN," In: Proceedings of the 2019 ACM Symposium on SDN Research, pp. 140–151 (2019). https://doi.org/10.1145/3314148.3314357
[7]Boutaba, R., et al. "A comprehensive survey on machine learning for networking: evolution, applications and research opportunities," J. Internet Serv. Appl. 9(1), 16 (2018). https://doi.org/10.1186/s13174-018-0087-2
[8]Suárez-Varela, J., et al. "The graph neural networking challenge: a worldwide competition for education in AI/ML for networks," SIGCOMM Comput. Commun. Rev. 51(3), 9–16 (2021). https://doi.org/10.1145/3477482.3477485
[9]Alshebaney, E.J.A. "Improving electrical energy distribution," Int. Acad. J. Sci. Eng. 11(1), 277–284 (2024). https://doi.org/10.9756/IAJSE/V11I1/IAJSE1132
[10]Mehta, A. "A review paper on security in mobile ad hoc network," (2015).
[11]Hussain, S., Fathima, S.M.H. "Federated learning-assisted coati deep learning-based model for intrusion detection in MANET," Int. J. Comput. Intell. Syst. 17(1), 1–15 (2024). https://doi.org/10.1007/s44196-024-00590-w
[12]Rani, S., Charaya, S. "Performance improvement of AODV routing protocol using Q-learning, SARSA and DQN algorithm based RL techniques," (2023). https://doi.org/10.21203/rs.3.rs-3268810/v1
[13]Pandey, P., Singh, R. "QoS based modified route discovery in MANET for multimedia applications," Multimed. Tools Appl. 82(19), 29671–29688 (2023). https://doi.org/10.1007/s11042-023-14855-7
[14]Maret, Y., et al. "Investigation of a GNN approach to mitigate congestion in a realistic MANET scenario," Procedia Comput. Sci. 205, 127–136 (2022).
[15]Duraipandian, M. "Performance evaluation of routing algorithm for MANET based on the machine learning techniques," J. Trends Comput. Sci. Smart Technol. (TCSST) 1(1), 25–38 (2019).
[16]Hassan, S.M., et al. "Enhancing MANET security through federated learning and multiobjective optimization: a trust-aware routing framework," IEEE Access (2024). 10.1109/ACCESS.2024.3505236
[17]Jiang, W., et al. "Graph neural networks for routing optimization: challenges and opportunities," Sustainability 16(21), 9239 (2024). https://doi.org/10.3390/su16219239
[18]Danilchenko, K., et al. "Deep learning for MANET routing," IEEE Trans. Mach. Learn. Commun. Netw. 1, 412–424 (2023). 10.1109/TMLCN.2023.3324280
[19]"An adaptive, energy-efficient and secure routing protocol for zone-related mobile ad hoc networks using reinforcement learning," Sci. Rep. (2025). https://doi.org/10.1038/s41598-025-32918-7
[20]Dev, A., et al. "Energy-efficient routing algorithms for mobile ad hoc networks," J. Wirel. Mob. Netw. Ubiquitous Comput. Depend. Appl. 16(2), 332–345 (2025). DOI: 10.58346/JOWUA.2025.I2.021
[21]Arulselvan, G., Rajaram, A. "Routing attacks detection in MANET using trust management enabled hybrid machine learning," Wirel. Netw. 31(2), 1481–1495 (2025). https://doi.org/10.1007/s11276-024-03846-7