Discrete algebra-based neural models for secure information transmission

Patil, Deepak B.; Kale, Vaishnaw G.; Patil, Shubhangi Babasaheb; Rajmane, Amol Bapuso; Joshi, Sagar Vasantrao; Pawase, Trupti Narayan

doi:10.47974/JDMSC-2429

Open Access Research Article

Discrete algebra-based neural models for secure information transmission

Deepak B. Patildeepakp@isquareit.edu.inDepartment of Data Science Engineering School of Engineering and Management D Y Patil Education Society (Deemed to be University)Kolhapur, Maharashtra, 416006, IndiaView full profile → , Vaishnaw G. Kalevaishnaw25@gmail.comSchool of Computer Science Engineering and Applications D Y Patil International University AkurdiPune, Maharashtra, 411044, IndiaView full profile → , Shubhangi Babasaheb Patilpatilsb0908@gmail.comDepartment of Electronics and Telecommunication Dr J J Magdum College of EngineeringJaysingpur, Maharashtra, 416101, IndiaView full profile → , Amol Bapuso Rajmaneamolbrajmane@gmail.comDepartment of Computer Science & Engineering School of Computational Sciences JSPM UniversityPune, Maharashtra, 412207, IndiaView full profile → , ^*Sagar Vasantrao JoshiCorresponding authorsagar.joshi@nmiet.edu.inDepartment of Electronics & Telecommunication Engineering Nutan Maharashtra Institute of Engineering and Technology Talegaon DabhadePune, Maharashtra, 410507, IndiaView full profile → , Trupti Narayan Pawasetpawase@gmail.comSchool of Engineering and Technology DES Pune UniversityPune, Maharashtra, 411004, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 2125–2136Vol. 28Issue 5-BAugust 2025DOI: 10.47974/JDMSC-2429 Crossmark XML

Received:: 05 Nov 2024
Published Online:: 30 Aug 2025
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-2429
Pages:: 2125–2136

Abstract

Secure and reliable transmission over noisy and adversarial channels remains a critical challenge in modern communication systems. We introduce a discrete algebra–driven neural framework that embeds finite-field arithmetic directly into learned encoding and decoding layers, combining classical error-correcting code structures with trainable neural masks. Evaluated on both AWGN and real-world packet-loss traces, our hybrid model achieves bit-error rates below 10–4 at 6 dB SNR—a tenfold improvement over Hamming codes—while reducing information leakage by 30 % compared to a pure neural autoencoder. Despite these gains, end-to-end latency remains under 0.8 ms per 128-bit block on a Google Colab T4 GPU. These results demonstrate that discrete algebra–aware neural architectures can jointly optimize reconstruction fidelity and confidentiality, offering a practical path to robust, secrecy-preserving communications under realistic threat models. Our training employs a joint loss combining mean-squared reconstruction error with a mutual-information penalty to enforce secrecy and incorporates ℓ∞-bounded adversarial perturbations for robustness. The resulting model generalizes across dynamically varying noise and loss patterns, preserving algebraic invariants while adapting to channel impairments. This work highlights the potential of integrating discrete algebraic theory with deep learning to achieve high-assurance communication in the presence of sophisticated eavesdroppers.

Keywords

Encrypted network traffic Anomaly detection Cryptanalysis-informed scoring Entropy analysis TLS/QUIC handshake Hybrid machine learning Adaptive thresholding

Subject Classifications

68Q11

References

[1] Z. Xu, S. Hong, and K. Zhang, “Graph neural network–based decoding of linear block codes,” IEEE Trans. Commun., vol. 70, no. 7, pp. 4169–4181 (Jul. 2022).
[2] N. Farsad and A. Goldsmith, “Neural turbo decoder: A deep learning–based iterative channel decoder for turbo codes,” IEEE Trans. Wireless Commun., vol. 20, no. 4, pp. 2103–2115 (Apr. 2021).
[3] Swati G. Kale, Smita N. Gambhire, Deepti Deshmukh, Dharmesh Dhabliya, Yeshil Bangera, and D. J. Dahigaonkar, “Leveraging machine learning for real-time optimization in large-scale information systems,” Journal of Information and Optimization Sciences, vol. 46, no. 4-B, pp. 1289–1301 (2025), doi: 10.47974/JIOS-1990.
[4] L. Xu, L. Song, and L. Hanzo, “Deep learning–aided secure network coding for wireless sensor networks,” IEEE Access, vol. 10, pp. 12345–12360 (2022).
[5] B. Chen, C. Li, and K. Kwong, “Efficient cyclic codes over prime fields,” IEEE Trans. Inf. Theory, vol. 67, no. 5, pp. 3168–3180 (May 2021).
[6] S. Cammerer and G. Caire, “Scaling neural belief propagation decoders to large blocklengths,” IEEE J. Sel. Areas Inf. Theory, vol. 1, no. 1, pp. 108–122 (May 2021).
[7] S. Liva and M. Chiani, “Protograph LDPC codes for the AWGN channel: Design, performance, and analysis,” IEEE Commun. Surv. Tutor., vol. 24, no. 1, pp. 316–345, 1st Quart. (2022).
[8] A. Raturi and S. S. C. Gonder, “New results in bipolar controlled b-dislocated metric space and its applications for solving fractional differential equations,” J. Interdiscip. Math., vol. 27, no. 8, pp. 1797–1803 (2024).
[9] P. Mathur, F. Sheth, D. Goyal, and A. K. Gupta, “Deep insight: Mathematical modeling and statistical analysis for mango leaf disease classification using advanced deep learning models,” J. Interdiscip. Math., vol. 27, no. 2, pp. 317–342 (2024), doi: 10.47974/JIM-1830.

Views: 181Downloads: 6Citations: 0

Journal of Discrete Mathematical Sciences and Cryptography

Discrete algebra-based neural models for secure information transmission

Abstract

Keywords

Subject Classifications

References