Graph neural networks for cryptographic key prediction analysis
Tanya Singhdean.academics@niu.edu.inDepartment of Computer Science & EngineeringNoida International UniversityGreater Noida, Uttar Pradesh, 203201, IndiaView full profile → , *Ramesh SainiCorresponding authorramesh.saini.orp@chitkara.edu.inCentre for Research Impact & OutcomeChitkara University Institute of Engineering and TechnologyChitkara UniversityRajpura, Punjab, 140401, IndiaView full profile → , Amit Kansalamit.kansal@quantumeducation.inQuantum University Research CenterQuantum UniversityRoorkee, Uttarakhand, 247667, India0009-0006-5541-8289View full profile → , Madireddy SirishaMadireddySirisha2024@protonmail.comCentre for Multidisciplinary ResearchAnurag UniversityHyderabad, Telangana, 500088, India0009-0003-6831-4452View full profile → , Preeti Pandurang Kalepreetikale2025@gmail.comDepartment of Electronics & Computer EngineeringCSMSS Chh. Shahu College of EngineeringChhatrapati Sambhajinagar, Maharashtra, 431011, IndiaView full profile → , Yagna B. Adhyaruybadhyaru.ce.hcet@gokuluniversity.ac.inFaculty of EngineeringGokul Global UniversitySidhpur, Gujarat, 384151, 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-3080
- Pages:
- 4647–4658
Abstract
The article addresses the growing challenge of analyzing the cryptographic key predictability in the era of the high-tech artificial intelligence and data-driven cybersecurity. Computational infeasible Classical cryptanalysis (like brute-force, statistical models) lacks a model of rich relational interactions among cryptographic processes. The study will overcome them by proposing a new Graph Neural Network (GNN)-based model which views the cryptographic key generation as a graph-structured data, and the latent structural patterns can be mined. The methodology involves the combination of graph construction, feature embedding and multi-architecture GNN learning (GCN, GAT, GraphSAGE) and optimized training strategies. Experimental evaluation of synthetic and benchmark data results indicate high performance with 89.3 percent accuracy, 0.88 precision, 0.87 recall, and 0.89 bits entropy reduction, which is better than statistical, machine learning and deep learning baselines. The proposed model is described as having a higher prediction capacity and a lower computational cost (38 ms inference time). The publication contributes to a systematic analysis of cryptography and offers novel insights into how to detect the leakage of entropy and design secure systems.
Keywords
Subject Classifications
References
[1] A. B. Ajmal, S. Khan, M. Alam, A. Mehbodniya, J. Webber, and A. Waheed, “Toward effective evaluation of cyber defense: Threat based adversary emulation approach,” IEEE Access, vol. 11, pp. 70443–70458 (2023).
[2] T. Birkstedt, M. Minkkinen, A. Tandon, and M. Mäntymäki, “AI governance: Themes, knowledge gaps and future agendas,” Internet Res., vol. 33, no. 7, pp. 133–167 (2023).
[3] S. Dasgupta, A. Piplai, P. Ranade, and A. Joshi, “Cybersecurity knowledge graph improvement with graph neural networks,” in Proc. IEEE Int. Conf. Big Data (Big Data), Orlando, FL, USA, pp. 3290–3297 (Dec. 15–18, 2021).
[4] M. François, P. E. Arduin, and M. Merad, “Classification of decision support systems for cybersecurity,” in Proc. 15th Mediterranean Conf. Inf. Syst. (MCIS) and 6th Middle East & North Africa Conf. Digital Inf. Syst. (MENACIS), Madrid, Spain (Sep. 6–9, 2023).
[5] C. Mudimannan, S. S. Bhati, A. Shelke, P. Dhabe, K. R. Kumar, and C. K. Veni, “Strategic approaches to enhancing data security in intelligent power networks through technology and policy,” J. Discrete Math. Sci. Cryptogr., vol. 29, no. 2-A, pp. 411–419 (2026), doi: 10.47974/JDMSC-2472.
[6] M. Gupta, C. Akiri, K. Aryal, E. Parker, and L. Praharaj, “From ChatGPT to ThreatGPT: Impact of generative AI in cybersecurity and privacy,” IEEE Access, vol. 11, pp. 80218–80245 (2023).
[7] W. Hong, J. Yin, M. You, H. Wang, J. Cao, J. Li, M. Liu, and C. Man, “A graph empowered insider threat detection framework based on daily activities,” ISA Trans., vol. 141, pp. 84–92 (2023).
[8] K. R. Praneeth, H. M. A. Ghanimi, M. S. Narayana, N. Kafila, B. R. Kumar, S. Sengan, and P. Dadheech, “A cyber-physical system with blockchain integrated chaotic secure hash algorithms-256 for secured supply chain management system,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 5-B, pp. 1935–1944 (2025), doi: 10.47974/JDMSC-2369.
[9] J. Jacobs, S. Romanosky, O. Suciu, B. Edwards, and A. Sarabi, “Enhancing vulnerability prioritization: Data-driven exploit predictions with community-driven insights,” in Proc. IEEE Eur. Symp. Secur. Privacy Workshops (EuroS&PW), Delft, The Netherlands, pp. 194–206 (Jul. 3–7, 2023).
[10] P. Liashchynskyi and P. Liashchynskyi, “Grid search, random search, genetic algorithm: A big comparison for NAS,” arXiv preprint arXiv:1912.06059 (2019).
[11] T. T. Nguyen and V. J. Reddi, “Deep reinforcement learning for cyber security,” IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 8, pp. 3779–3795 (2023).
[12] V. S. Nalawade, S. S. Sharad, T. P. Dhananjay, S. S. Popat, and W. S. Baban, “A comprehensive survey on mobile theft prevention systems: Innovations and approaches for enhanced security,” Int. J. Electr. Electron. Comput. Syst., vol. 13, no. 2, pp. 46–50 (2025), doi: 10.65521/ijeecs.v13i2.14.
[13] E. Tabassi, “Artificial intelligence risk management framework (AI RMF 1.0),” National Institute of Standards and Technology, Gaithersburg, MD, USA, NIST AI 100-1 (2023), doi: 10.6028/NIST.AI.100-1.
[14] R. C. Poonia, R. Almakki, A. K. J. Saudagar, A. Altameem, and M. Albathan, “A detailed examination of LSTM networks for large-scale text generation with optimizing sequence models,” J. Inf. Optim. Sci., vol. 45, no. 5, pp. 1477–1486 (2024), doi: 10.47974/JIOS-1769.
