Optimizing network security response through graph-based detection of suspicious activities and recovery strategies
Y. M. Manjunathasvcet21@gmail.comDepartment of MathematicsBGS Institute of TechnologyAdichunchanagiri UniversityBG Nagar, Nagamangala Taluk, Mandya, Karnataka, 571811, IndiaView full profile → , *H. L. ParashivamurthyCorresponding authorparashivamurthyhl@bgsit.ac.inDepartment of MathematicsBGS Institute of TechnologyAdichunchanagiri UniversityBG Nagar, Nagamangala Taluk, Mandya, Karnataka, 571811, IndiaView full profile → , S. Girish Babugirishbabu.s@rrit.ac.inDepartment of MathematicsR R Institute of Technology`Bangalore, Karnataka, 560090, IndiaView full profile → , G. Manjunathmanjunath.g@rrit.ac.inDepartment of MathematicsR R Institute of TechnologyBangalore, Karnataka, 560090, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Jan 2026
- Published Online:
- 31 Aug 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2233
- Pages:
- 2903–2916
Abstract
This paper presents a graph-based method of identifying suspicious activities and improving recovery efforts in response to the increasing complexity of network security threats. The proposed approach assumes that the network can be modeled as a dynamic graph where devices represent nodes and communication links represent the edges of the graph: graph theory will be used to identify anomalies based on centrality and clustering measures. The system tracks the performance of the network real-time, detecting a deviation that could mean breach of security. When it observes suspicious behavior, the technique activates autonomous recovery mechanisms, such as isolating nodes, rerouting traffic and recovering backup configuration so that the service is impacted significantly. According to the experimental findings, it can be seen that the proposed solution is much better than current methods and has a detection rate of 95, recovery time is 30 seconds when dealing with DDoS attacks and that network services are much less affected by such attacks. The suggested approach does not only increase the detection accuracy, but it also boosts its recovery efficiency, which results in quicker operations in the network. The findings point to the role that graph-based models could play in handling the contemporary cybersecurity issues.
Keywords
Subject Classifications
References
[1] L.-X. Zheng, X.-L. Xu, J. Li, L. Zhang, X.-C. Pan, Z.-Y. Ma, and L.-H. Zhang, “Malicious URL prediction based on community detection,” in 2015 Int. Conf. Cyber Security of Smart Cities, Industrial Control System and Communications (SSIC), Shanghai, China, pp. 1–7 (2015).
[2] P. Bi, Q. Wang, Y. Xu, T. Zang, and X. Yun, “Pegasus: Accelerating provenance graph-based intrusion detection methods,” in 2025 28th Int. Conf. Computer Supported Cooperative Work in Design (CSCWD), Compiegne, France, pp. 2436–2441 (2025).
[3] R. Ge, Y. Zhang, C. Si, G. Zhou, and W. Zhou, “MateGraph: Toward mobile malware detection through traffic behavior graph,” in 2022 IEEE 24th Int. Conf. High Performance Computing & Communications; 8th Int. Conf. Data Science & Systems; 20th Int. Conf. Smart City; 8th Int. Conf. Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys), Hainan, China, pp. 801–809 (2022).
[4] X. Ma, C. Zheng, Z. Li, J. Yin, Q. Liu, and X. Chen, “A lightweight graph-based method to detect pornographic and gambling websites with imperfect datasets,” in 2022 IEEE Int. Conf. Trust, Security and Privacy in Computing and Communications (TrustCom), Wuhan, China, pp. 291–298 (2022).
[5] S. A. Patil, J. K. Patil, and S. Singh, “A novel cryptographic approach to evaluate the security of federated learning frameworks,” J. Discrete Mathematical Sciences and Cryptography, vol. 28, no. 5-A, pp. 1527–1536 (2025).
[6] P. Sarma and M. Rahman, “Mathematical analysis of wavelet-based multi-image compression in medical diagnostics,” J. Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-B, pp. 675–687 (2024).
[7] Q. Xu, S. Yang, L. Xu, and D. Zhao, “Android malware detection method based on graph convolutional networks,” in 2024 Int. Conf. Artificial Intelligence and Power Systems (AIPS), Chengdu, China, pp. 95–98 (2024).
[8] L. Hailin, W. Yadi, and H. Jihong, “A novel method for modeling complex network of software system security,” in 2012 IEEE Sixth Int. Conf. Software Security and Reliability Companion, Gaithersburg, MD, USA, pp. 24–26 (2012).
[9] R. S. Kumar and K. D. V. Prasad, “Securing digital authentication with cryptographic innovations in intrinsic verification systems,” J. Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-A, pp. 317–328 (2024).
[10] N. Hussain, S. K. Dixit, and A. K. Gupta, “A novel approach of unsupervised feature selection using iterative shrinking and expansion algorithm,” J. Interdisciplinary Mathematics, vol. 26, no. 3, pp. 519–530 (2023).
[11] Y. Luo, M. He, and X. Wang, “Analyzing the semantic structure of network flow: A threat detection method with independent generalization capabilities,” IEEE Trans. Netw. Sci. Eng., vol. 12, no. 1, pp. 28–43 (Jan./Feb. 2025).
[12] N. Khokhlov, S. Kanavin, and A. Rybokitov, “Modeling information security infringements in mobile self-organizing network of communication using fuzzy logic and theory of graphs,” in Proc. 2019 1st Int. Conf. Control Syst., Math. Model., Autom. Energy Efficiency (SUMMA), Lipetsk, Russia, pp. 60–63 (2019).
[13] Y. Huang and D. Li, “Design of malicious software classification and recognition algorithms based on graph theory in computer networks,” in 2024 Int. Conf. Interactive Intelligent Systems and Techniques (IIST), Bhubaneswar, India, pp. 593–597 (2024).
[14] A. Torres and G. Anders, “Spectral graph theory and network dependability,” in Proc. 2009 4th Int. Conf. Dependability Comput. Syst., Brunów, Poland, pp. 356–363 (2009).
[15] F. Zhang and B. Bu, “A cyber security risk assessment methodology for CBTC systems based on complex network theory and attack graph,” in Proc. 2021 7th Annu. Int. Conf. Netw. Inf. Syst. Comput. (ICNISC), Guiyang, China, pp. 15–20 (2021).
[16] A. S. Odyuo, P. Mercy, and M. K. Patel, “Fibonacci range labeling on direct product and union of graphs,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 7, pp. 2671–2678 (2025).
[17] W. Jiang, B.-X. Fang, H.-L. Zhang, Z.-H. Tian, and X.-F. Song, “Optimal network security strengthening using attack-defense game model,” in Proc. 2009 6th Int. Conf. Inf. Technol.: New Generations, Las Vegas, NV, USA, pp. 475–480 (2009).
[18] V. Sivakumar, A. K. Verma, P. Kumar, N. Saw, and V. H. Krishnan, “Fraud detection in financial transaction using GNN,” in Proc. 2025 Int. Conf. Visual Analytics Data Visualization (ICVADV), Tirunelveli, India, pp. 724–730 (2025).
[19] Ö. Sen, C. Eze, A. Ulbig, and A. Monti, “On holistic multi-step cyberattack detection via a graph-based correlation approach,” in Proc. 2022 IEEE Int. Conf. Commun., Control, Comput. Technol. Smart Grids (SmartGridComm), Singapore, pp. 380–386 (2022).
[20] K. Zhu, J. Pan, Y. Yang, Y. Bai, R. Xu, and J. Li, “ICGINet: Intra-temporal and cross-temporal graph interaction network for misaligned bitemporal remote sensing image change detection,” IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–15 (2025).
