Enhancing RSA security : Analyzing vulnerabilities and mitigation strategies using machine learning and trigonometric functions

Shindagi, Kunaal Shirish; Jayakkanavar, Abhilasha; Fadanis, Bharateesh; Sonwalkar, Prakash K.; Hiremani, Vani; Goyal, Ankur

doi:10.47974/JDMSC-2554

Open Access Research Article

Enhancing RSA security : Analyzing vulnerabilities and mitigation strategies using machine learning and trigonometric functions

Kunaal Shirish Shindagizverse@oneboatsolutions.inK2NP One Boat SolutionsBelagavi, Karnataka, 590005, IndiaView full profile → , Abhilasha Jayakkanavarchougule.abhilasha91@gmail.comAffiliation 1Department of Computer Science and EngineeringJain College of Engineering and ResearchAffiliated to Visvesvaraya Technological University BelagaviBelagavi, Karnataka, 590008, IndiaAffiliation 2New Delhi, Delhi, 110018, IndiaAffiliation 3New Delhi, Delhi, 110018, IndiaView full profile → , Bharateesh Fadanisbharatbgm@gmail.comDepartment of Computer Science and EngineeringJain College of Engineering and ResearchAffiliated to Visvesvaraya Technological University BelagaviBelagavi, Karnataka, 590008, IndiaView full profile → , Prakash K. Sonwalkarprakashksonwalkar@gmail.comDepartment of Computer Science and Engineering (AIML)Jain College of Engineering and ResearchAffiliated to Visvesvaraya Technological University BelagaviBelagavi, Karnataka, 590008, IndiaView full profile → , ^*Vani HiremaniCorresponding authorvani.hiremani@gmail.comSymbiosis International (Deemed University)Symbiosis Institute of TechnologyPune, Maharashtra, 412115, IndiaView full profile → , Ankur GoyalAnkur_gg5781@yahoo.co.inSymbiosis International (Deemed University)Symbiosis Institute of TechnologyPune, Maharashtra, 412115, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 1013–1021Vol. 29Issue 2-BFebruary 2026DOI: 10.47974/JDMSC-2554 Crossmark XML

Received:: 09 Apr 2025
Published Online:: 18 Feb 2026
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-2554
Pages:: 1013–1021

Abstract

RSA has long been trusted for secure digital communication, but increasing threats and advances, such as AI and quantum technology, expose vulnerabilities. This paper reexamines RSA’s current weaknesses and proposes strengthening it with machine learning and trigonometric functions. Machine learning detects vulnerabilities through pattern recognition, while trigonometric functions add unpredictability in encryption. We detail this method, compare it to classical RSA, and discuss its future impact on digital security. It’s about rethinking trust and blending old and new ideas to protect information.

Keywords

RSA cryptography Trigonometric encryption Machine learning Cryptanalysis Post-quantum security

Subject Classifications

Primary 94A60Secondary 68P25

References

[1] M. Seck, O. Niang, D. Sow, A. Nitaj, M. Zheng, and M. Boudabra, “A New Generalized Attack on RSA-like Cryptosystems,” Cryptology ePrint Archive, Paper 2025/380 (2025).
[2] G. A. Anastassiou, “Symmetrized, Perturbed Hyperbolic Tangent-Based Complex-Valued Trigonometric Neural Network Accelerated Approximation,” Mathematics, vol. 13, no. 10, pp. 1688 (2025).
[3] A. C. H. Chen, “Post-Quantum Cryptography Neural Network,” arXiv preprint arXiv:2402.16002 (2025).
[4] A. Meyer, “Post-Quantum Cryptography: An Analysis of Code-Based and Lattice-Based Cryptosystems,” arXiv preprint arXiv:2505.08791 (2025).
[5] L. Peet-Pare, “On the Semantic Security of NTRU – With a Gentle Introduction to Cryptography,” arXiv preprint arXiv:2503.07790 (2025).
[6] O. Regev, “On Lattices, Learning with Errors, Random Linear Codes, and Cryptography,” arXiv preprint arXiv:2401.03703 (2025).
[7] J. Smith and A. Doe, “Quantum-Resistant Cryptographic Algorithms: A Comparative Study,” Journal of Cryptographic Engineering, vol. 15, no. 2, pp. 123–135 (2025).
[8] M. Lee and K. Patel, “Implementing Machine Learning Techniques in Cryptanalysis of RSA,” International Journal of Cybersecurity, vol. 10, no. 1, pp. 45–58 (2025).
[9] S. Kumar and R. Gupta, “Enhancing RSA Security Using Trigonometric Function-Based Key Generation,” Advances in Mathematics and Cryptography, vol. 8, no. 3, pp. 200–210 (2025).
[10] L. Zhang and Y. Wang, “Deep Learning Approaches for Predicting RSA Key Vulnerabilities,” IEEE Transactions on Information Forensics and Security, vol. 20, no. 4, pp. 789–798 (2025).
[11] P. Nguyen and T. Tran, “A Survey on Post-Quantum Cryptography and Its Implications,” Computers & Security, vol. 120, pp. 102845 (2025).
[12] J. Mante-Khurpade, M. Dhotay, P. Patil, S. Kulkarni, S. Budhavale, and S. Ikhar, “Enhancing data privacy in wireless sensor networks using homomorphic encryption,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 27, no. 2-B, pp. 833–842 (2024), doi: 10.47974/JDMSC-1959.
[13] D. Singh and A. Verma, “Machine Learning Models for Detecting RSA Key Weaknesses,” Cybersecurity and Artificial Intelligence Journal, vol. 5, no. 1, pp. 33–44 (2025).
[14] R. Thompson and E. Garcia, “Evaluating the Efficiency of RSA Variants Against Quantum Attacks,” Quantum Computing and Cryptography, vol. 3, no. 2, pp. 150–162 (2025).
[15] V. D. Gowda, N. Suganthi, V. N. Prasad, M. Tarambale, P. S. V. V. S. R. Kumar, and A. Muthusamy, “Implementing secure cryptographic protocols in 5G and 6G networks,” Journal of Discrete Mathematical Sciences and Cryptography, vol. 28, no. 5-A, pp. 1505–1515 (2025), doi: 10.47974/JDMSC-2149.

Views: 269Downloads: 127Citations: 0