Graph-partition-based attack mitigation in dense mesh networks
Sangeeta Vhatkarvhatkarsangeeta@gmail.comDepartment of Information TechnologyThakur College of Engineering & TechnologyMumbai, Maharashtra, 400101, IndiaView full profile → , Rupali Manerupali.mane@thakureducation.orgDepartment of Electronics & Telecommunication EngineeringThakur College of Engineering & TechnologyMumbai, Maharashtra, 400101, IndiaView full profile → , Sukruti Kaulgudsukruti.kaulgud@thakureducation.orgDepartment of Electronics & Telecommunication EngineeringThakur College of Engineering & TechnologyMumbai, Maharashtra, 400101, IndiaView full profile → , Asmita Bhupesh Maratheasmitamarathe@tcetmumbai.inDepartment of Computer Science and Engineering (Cyber Security)Thakur College of Engineering & TechnologyMumbai, Maharashtra, 400101, IndiaView full profile → , Anand Arvind Mahaanandmaha007@gmail.comDepartment of Artificial Intelligence & Machine LearningThakur College of Engineering & TechnologyMumbai, Maharashtra, 400101, IndiaView full profile → , *Zahir AalamCorresponding authorzahir_aalam@hotmail.comDepartment of Computer Science and Engineering (Cyber Security)Thakur College of Engineering & TechnologyMumbai, Maharashtra, 400101, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2026
- Published Online:
- 31 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-3005
- Pages:
- 3739–3749
Abstract
The attack mitigation technique, presented as graph-partition scheme, enhances the resistance of dense mesh communication network to the fast spreading cyber-attacks. The research work presents an adaptive graph-partitioning framework that incorporates Louvain’s community detection, METIS’s multi-level partitioning and multi-objective optimization for optimal attack containment. The framework is designed to achieve minimal reverse propagation while maximizing latency, connectivity, load balancing and routing stability in dynamic environments. The Pareto configurations of partitions are obtained by using NSGA-II and Particle Swarm Optimization. Dynamic adaptive partitioning also allows for the protection against wormhole, Sybil and DDoS attacks. Experimental results show that a real-time distributed mesh infrastructure becomes more scalable, resilient and secure with low communication overheads.
Keywords
Subject Classifications
References
[1] M. Oehlers and B. Fabian, “Graph metrics for network robustness—A survey,” Mathematics, vol. 9, no. 8, Art. no. 895 (2021), doi: 10.3390/math9080895.
[2] K. Koo, D. Moon, J.-H. Huh, S.-H. Jung, and H. Lee, “Attack graph generation with machine learning for network security,” Electronics, vol. 11, no. 9, Art. no. 1332 (2022), doi: 10.3390/electronics11091332.
[3] F. Miao, X. Zhou, S. Xiao, and S. Zhang, “A graph similarity algorithm based on graph partitioning and attention mechanism,” Electronics, vol. 13, no. 19, Art. no. 3794 (2024), doi: 10.3390/electronics13193794.
[4] Y. Listiana, L. Susilowati, S. Slamin, and K. Dliou, “The central local metric dimension of graphs with a single central vertex,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 28, no. 6, pp. 2297–2308 (2025), doi: 10.47974/JDMSC-2228.
[5] P. Khobragade, B. Thakran, P. K. Dhankar, P. Dasarwar, C. Vaidya, and K. Dhote, “Improving intrusion detection systems using machine learning algorithms for real-time network security monitoring,” in Proc. 1st Int. Conf. Data Science and Intelligent Network Computing (ICDSINC), Raipur, India, pp. 160–165 (2025), doi: 10.1109/ICDSINC66221.2025.11448255.
[6] S. Karageorgiou and V. Karyotis, “Markov-based malware propagation modeling and analysis in multi-layer networks,” Network, vol. 2, no. 3, pp. 456–478 (2022), doi: 10.3390/network2030028.
[7] V. Yadav, A. P. Kharade, A. Rawat, D. S. Asudani, and K. Anitha, “Strategic investment approaches for building robust computer security frameworks within organizational networks,” Journal of Information and Optimization Sciences, vol. 47, no. 5-A, pp. 1661–1669 (2026), doi: 10.47974/JIOS-2256.
[8] S. Charkhabi, P. Samimi, S. S. Bagui, D. Mink, and S. C. Bagui, “Node classification of network threats leveraging graph-based characterizations using Memgraph,” Computers, vol. 13, no. 7, Art. no. 171 (2024), doi: 10.3390/computers13070171.
[9] A Cilfone, L. Davoli, L. Belli, and G. Ferrari, “Wireless mesh networking: An IoT-oriented perspective survey on relevant technologies,” Future Internet, vol. 11, no. 4, Art. no. 99 (2019), doi: 10.3390/fi11040099.
[10] M. Kalinin, E. Zavadskii, and A. Busygin, “A graph-based technique for securing the distributed cyber-physical system infrastructure,” Sensors, vol. 23, no. 21, Art. no. 8724 (2023), doi: 10.3390/s23218724.
[11] R. C. Poonia, T. Singh, C. K. Rajashri, D. Mondal, and S. M. Patil, “Optimizing communication system security through comprehensive testing and intelligent network configurations,” Journal of Information and Optimization Sciences, vol. 47, no. 5-A, pp. 1709–1717 (2026), doi: 10.47974/JIOS-2261.
[12] X. Zhang, B. Hu, S. Liu, Q. Sun, and L. Chen, “AttenFlow: Context-aware architecture with consensus-based retrieval and graph attention for automated document processing,” Applied Sciences, vol. 15, no. 13, Art. no. 7517 (2025), doi: 10.3390/app15137517.
[13] D. Kanellopoulos, V. K. Sharma, T. Panagiotakopoulos, and A. Kameas, “Networking architectures and protocols for IoT applications in smart cities: Recent developments and perspectives,” Electronics, vol. 12, no. 11, Art. no. 2490 (2023), doi: 10.3390/electronics12112490.
[14] M. François, P.-E. Arduin, and M. Merad, “Physics-informed graph neural networks for attack path prediction,” Journal of Cybersecurity and Privacy, vol. 5, no. 2, Art. no. 15 (2025), doi: 10.3390/jcp5020015.
