Secure multi-party computation in deep learning : Enhancing privacy in distributed neural networks

Sagar, P. Vidya; Ghanimi, Hayder M. A.; Prabhu, L. Arokia Jesu; Raja, L.; Dadheech, Pankaj; Sengan, Sudhakar

doi:10.47974/JDMSC-1879

Open Access Research Article

Secure multi-party computation in deep learning : Enhancing privacy in distributed neural networks

^*P. Vidya SagarCorresponding authorpvsagar20@gmail.comDepartment of Computer Science & Engineering Koneru Lakshmaiah Education FoundationVaddeswaram, Andhra Pradesh, 522302, IndiaView full profile → , Hayder M. A. Ghanimihayder.alghanami@uowa.edu.iqDepartment of Information Technology College of Science University of Warith Al-Anbiyaa; Department of Computer Science College of Computer Science and Information Technology University of KerbalaDepartment of Information Technology College of Science University of Warith Al-AnbiyaaKarbala, 5751, IraqView full profile → , L. Arokia Jesu Prabhuarokiajeruprabhu@gmail.comDepartment of Computer Science and Engineering CMR Institute of TechnologyHyderabad, Telangana, IndiaView full profile → , L. Rajaraja.lece@sece.ac.inDepartment of Electronics and Communication Engineering Sri Eshwar College of EngineeringCoimbatore, Tamil Nadu, IndiaView full profile → , Pankaj Dadheechpankajdadheech777@gmail.comDepartment of Computer Science & Engineering Swami Keshvanand Institute of Technology Management & Gramothan (SKIT)Department of Computer Science & Engineering Swami Keshvanand Institute of Technology, Management & GramothanJaipur, Rajasthan, 302017, IndiaView full profile → , Sudhakar Sengansudhasengan@gmail.comDepartment of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli, Tamil Nadu, 627152, IndiaView full profile →

* Corresponding author · click or hover a name for details

pp. 249–259Vol. 27Issue 2-AMarch 2024DOI: 10.47974/JDMSC-1879 Crossmark XML

Published Online:: 06 Apr 2024
Article type:: Research Article
Language:: EN
Article no.:: JDMSC-1879
Pages:: 249–259

Abstract

Ensuring data privacy while applying Deep Learning (DL) on distributed datasets represents an essential task in the current period of critical data security. Data privacy and accuracy of models are typically impacted by traditional methods. Data privacy is of the most tremendous significance in distributed data settings, and the current research presents a novel model for DL termed Secure Multi-Party Computation (SMPC). The accuracy of the mathematical models and confidentiality of the data are frequently compelled to coexist in conventional methods. In order to enable collaborative DL without compromising private information, the recommended system uses the Paillier Homomorphic Encryption Scheme (PHES). By using innovative cryptographic methods, this decentralized method secures the confidentiality of data without utilizing a Trusted Authority (TA). By performing a thorough assessment of the CIFAR-10 and IMDB datasets, the present study demonstrates that the system the author uses is simple and scalable and that it offers accuracy on par with conventional methods. By presenting an approach for achieving a balance between the two competing demands of data security and computational performance, this method signifies a vast advance forward with a confidentiality DL.

Keywords

Deep learning Encryption Data security Multi-Party computation Scalability Privacy

Subject Classifications

94B35

References

[1] Sayyad, S., Privacy-preserving deep learning using secure multiparty computation. 2nd IEEE International Conference on Inventive Research in Computing Applications, p. 139-142 (2020).
[2] B. Knott et al., Crypten: Secure multi-party computation meets machine learning—advances in Neural Information Processing Systems, 34, 4961-4973 (2021).
[3] Sharma, Sandeep Kumar, Kumar, Anil, Ashtagi, Rashmi & Jain, Rekha. OCA: An intelligent model for improving security breach of biometric based authentication systems, Journal of Discrete Mathematical Sciences and Cryptography, 26:5, 1415–1425 (2023), DOI: 10.47974/JDMSC-1765.
[4] Byrd, D., & Polychroniadou, A. Differentially private, secure multi-party computation for federated learning in financial applications. In Proceedings of the 1st ACM International Conference on AI in Finance, pp. 1-9 (2020).
[5] Bautista, O. G., & Akkaya, K. Network-efficient pipelining-based secure multiparty computation for machine learning applications. IEEE 47th Conference on Local Computer Networks (LCN), pp. 205-213 (2022).
[6] E. Marquet, J. Moeyersons, E. Pohle, M. V. Kenhove, A. Abidin and B. Volckaert, “Secure Key Management for Multi-Party Computation in MOZAIK,” IEEE European Symposium on Security and Privacy Workshops, Delft, Netherlands, pp. 133-140 (2023).
[7] S. P. Sanon, R. Reddy, C. Lipps and H. D. Schotten, “Secure Federated Learning: An Evaluation of Homomorphic Encrypted Network Traffic Prediction,” IEEE 20th Consumer Communications & Networking Conference, Las Vegas, NV, USA, pp. 1-6 (2023).
[8] C. Dong et al., “Maliciously Secure and Efficient Large-Scale Genome-Wide Association Study With Multi-Party Computation,” IEEE Transactions on Dependable and Secure Computing, vol. 20, no. 2, pp. 1243-1257 (2023).
[9] B. Rajalakshmi, “Exploring Cryptographic Paradigms for Secure Cloud Computing,” 2nd International Conference on Augmented Intelligence and Sustainable Systems, Trichy, India, pp. 1290-1294 (2023).
[10] K. Iwamura and A. A. A. M. Kamal, “Communication-Efficient Secure Computation of Encrypted Inputs Using (k, n) Threshold Secret Sharing,” IEEE Access, vol. 11, pp. 51166-51184 (2023).
[11] A. V. Kumar, K. Monica, and K. Mandadi, “Data Privacy Over Cloud Computing using Multi-Party Computation,” International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), Bengaluru, India, pp. 262-267 (2023).
[12] W. Ruan, M. Xu, W. Fang, L. Wang, L. Wang, and W. Han, “Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy,” 2023 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA, pp. 1926-1943 (2023).
[13] W. J. Liu and Z. X. Li, “Secure and Efficient Two-Party Quantum Scalar Product Protocol With Application to Privacy-Preserving Matrix Multiplication,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 70, no. 11, pp. 4456-4469 (2023).

Views: 326Downloads: 7Citations: 4