A Novel Privacy-Preserving Algorithm for Secure Data Sharing in Federated Learning Frameworks

Fahmy Ferdian Dalimarta; Nina Faoziyah; Doni Setiawan

doi:10.47709/cnahpc.v7i1.5385

Authors

Fahmy Ferdian Dalimarta Universitas Muhammadiyah Tegal, Indonesia
Nina Faoziyah Universitas Muhammadiyah Tegal, Indonesia
Doni Setiawan Universitas Muhammadiyah Tegal, Indonesia

DOI:

https://doi.org/10.47709/cnahpc.v7i1.5385

Keywords:

Data Security, Differential Privacy, Federated Learning, Homomorphic Encryption, Privacy-Preserving Algorithm

Abstract

Federated Learning (FL) has emerged as a promising paradigm for the collaborative training of machine learning models across decentralized devices while preserving data privacy. However, ensuring data security and privacy during model updates remains a critical challenge, particularly in scenarios that involve sensitive data. This study proposes a novel Privacy-Preserving Algorithm (PPA-FL) designed to enhance data security and mitigate privacy leakage risks in FL frameworks. The algorithm integrates advanced encryption techniques, such as homomorphic encryption, with differential privacy to secure model updates without compromising the utility. Furthermore, it incorporates a dynamic noise-adjustment mechanism to adaptively balance privacy and model accuracy. Extensive experiments on benchmark datasets demonstrate that PPA-FL achieves a competitive trade-off between privacy protection and model performance compared to existing methods. The proposed approach is computationally efficient and scalable, making it suitable for real-world applications in healthcare, finance, and the IoT environment. This research contributes to advancing secure data-sharing practices in federated learning, fostering the broader adoption of privacy-preserving machine learning solutions.

Downloads

Download data is not yet available.

References

Agarwal, P., & Shrivastava, P. (2021). Enhancing Data Security in Cloud Computing through Homomorphic Encryption. Computology: Journal of Applied Computer Science and Intelligent Technologies, 1(1), 32–39. https://doi.org/10.17492/computology.v1i1.2104

Ali, A., Al-rimy, B. A. S., Alsubaei, F. S., Almazroi, A. A., & Almazroi, A. A. (2023). HealthLock: Blockchain-Based Privacy Preservation Using Homomorphic Encryption in Internet of Things Healthcare Applications. Sensors, 23(15), 6762. https://doi.org/10.3390/s23156762

Chatterjee, A., & Sengupta, I. (2018). Translating Algorithms to Handle Fully Homomorphic Encrypted Data on the Cloud. IEEE Transactions on Cloud Computing, 6(1), 287–300. https://doi.org/10.1109/TCC.2015.2481416

Cidem Dogan, D., & Altindis, H. (2020). Storage and Communication Security in Cloud Computing Using a Homomorphic Encryption Scheme Based Weil Pairing. Elektronika Ir Elektrotechnika, 26(1), 78–83. https://doi.org/10.5755/j01.eie.26.1.25312

Deng, L. (2012). The mnist database of handwritten digit images for machine learning research. IEEE Signal Processing Magazine, 29(6), 141–142.

Fan, T., & Cui, Z. (2021). Adaptive differential privacy preserving based on multi?objective optimization in deep neural networks. Concurrency and Computation: Practice and Experience, 33(20). https://doi.org/10.1002/cpe.6367

Idris, I. A., & issahku, F. Y. (2024). Advancing Wireless Sensor Network Security through the Implementation of Homomorphic Encryption for Secure and Private Image Processing. International Journal for Research in Applied Science and Engineering Technology, 12(1), 1464–1474. https://doi.org/10.22214/ijraset.2024.58180

Johnson, N., Near, J. P., & Song, D. (2018). Towards practical differential privacy for SQL queries. Proceedings of the VLDB Endowment, 11(5), 526–539. https://doi.org/10.1145/3187009.3177733

JUNG, K., LEE, H., & CHUNG, Y. D. (2021a). Differentially Private Neural Networks with Bounded Activation Function. IEICE Transactions on Information and Systems, E104.D(6), 905–908. https://doi.org/10.1587/transinf.2021EDL8007

JUNG, K., LEE, H., & CHUNG, Y. D. (2021b). Differentially Private Neural Networks with Bounded Activation Function. IEICE Transactions on Information and Systems, E104.D(6), 905–908. https://doi.org/10.1587/transinf.2021EDL8007

Jung, W., Lee, E., Kim, S., Kim, J., Kim, N., Lee, K., Min, C., Cheon, J. H., & Ahn, J. H. (2021). Accelerating Fully Homomorphic Encryption Through Architecture-Centric Analysis and Optimization. IEEE Access, 9, 98772–98789. https://doi.org/10.1109/ACCESS.2021.3096189

K L, A., & Nair, T. R. G. (2019). Data storage lock algorithm with cryptographic techniques. International Journal of Electrical and Computer Engineering (IJECE), 9(5), 3843. https://doi.org/10.11591/ijece.v9i5.pp3843-3849

Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images. 32–33. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf

Li, Y., Du, W., Han, L., Zhang, Z., & Liu, T. (2023a). A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy. Sensors, 23(23), 9305. https://doi.org/10.3390/s23239305

Li, Y., Du, W., Han, L., Zhang, Z., & Liu, T. (2023b). A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy. Sensors, 23(23), 9305. https://doi.org/10.3390/s23239305

Liu, B., Eric B. Blancaflor, Fang, T., & Cao, L. (2024). Privacy Protection Based on Federated Learning. Journal of Artificial Intelligence and Technology. https://doi.org/10.37965/jait.2024.0503

Liu, H., Peng, C., Tian, Y., Long, S., & Wu, Z. (2021). Balancing Privacy-Utility of Differential Privacy Mechanism: A Collaborative Perspective. Security and Communication Networks, 2021, 1–14. https://doi.org/10.1155/2021/5592191

Liu, H., Wu, Z., Zhou, Y., Peng, C., Tian, F., & Lu, L. (2018a). Privacy-Preserving Monotonicity of Differential Privacy Mechanisms. Applied Sciences, 8(11), 2081. https://doi.org/10.3390/app8112081

Liu, H., Wu, Z., Zhou, Y., Peng, C., Tian, F., & Lu, L. (2018b). Privacy-Preserving Monotonicity of Differential Privacy Mechanisms. Applied Sciences, 8(11), 2081. https://doi.org/10.3390/app8112081

Ma, J., Hu, J., & Peng, Z. (2024). Privacy Preservation of Nabla Discrete Fractional-Order Dynamic Systems. Fractal and Fractional, 8(1), 46. https://doi.org/10.3390/fractalfract8010046

Ngabo, C. I., & El Beqqali, O. (2019). Implementation of Homomorphic Encryption for Wireless Sensor Networks Integrated with Cloud Infrastructure. Journal of Computer Science, 15(2), 235–248. https://doi.org/10.3844/jcssp.2019.235.248

Park, C., Hong, D., & Seo, C. (2019). An Attack-Based Evaluation Method for Differentially Private Learning Against Model Inversion Attack. IEEE Access, 7, 124988–124999. https://doi.org/10.1109/ACCESS.2019.2938759

Park, C., Kim, Y., Park, J.-G., Hong, D., & Seo, C. (2021). Evaluating Differentially Private Generative Adversarial Networks Over Membership Inference Attack. IEEE Access, 9, 167412–167425. https://doi.org/10.1109/ACCESS.2021.3137278

Parker, K., Hale, M., & Barooah, P. (2022a). Spectral Differential Privacy: Application to Smart Meter Data. IEEE Internet of Things Journal, 9(7), 4987–4996. https://doi.org/10.1109/JIOT.2021.3107770

Parker, K., Hale, M., & Barooah, P. (2022b). Spectral Differential Privacy: Application to Smart Meter Data. IEEE Internet of Things Journal, 9(7), 4987–4996. https://doi.org/10.1109/JIOT.2021.3107770

Salim, M. M., Kim, I., Doniyor, U., Lee, C., & Park, J. H. (2021). Homomorphic Encryption Based Privacy-Preservation for IoMT. Applied Sciences, 11(18), 8757. https://doi.org/10.3390/app11188757

Shi, L., & Zhu, H. (2024). A study of user data privacy protection algorithms in the context of metaverse based on emotional AI IoT. Applied Mathematics and Nonlinear Sciences, 9(1). https://doi.org/10.2478/amns.2023.2.00636

Thantharate, P., Bhojwani, S., & Thantharate, A. (2024). DPShield: Optimizing Differential Privacy for High-Utility Data Analysis in Sensitive Domains. Electronics, 13(12), 2333. https://doi.org/10.3390/electronics13122333

Wang, H., Zhang, J., Lu, C., & Wu, C. (2021a). Privacy Preserving in Non-Intrusive Load Monitoring: A Differential Privacy Perspective. IEEE Transactions on Smart Grid, 12(3), 2529–2543. https://doi.org/10.1109/TSG.2020.3038757

Wang, H., Zhang, J., Lu, C., & Wu, C. (2021b). Privacy Preserving in Non-Intrusive Load Monitoring: A Differential Privacy Perspective. IEEE Transactions on Smart Grid, 12(3), 2529–2543. https://doi.org/10.1109/TSG.2020.3038757

Wang, Y., Kifer, D., & Lee, J. (2019). Differentially Private Confidence Intervals for Empirical Risk Minimization. Journal of Privacy and Confidentiality, 9(1). https://doi.org/10.29012/jpc.660

Yang, C., Qi, J., & Zhou, A. (2024). Wasserstein Differential Privacy. Proceedings of the AAAI Conference on Artificial Intelligence, 38(15), 16299–16307. https://doi.org/10.1609/aaai.v38i15.29565

Zhang, Y., Lu, Y., & Liu, F. (2023). A Systematic Survey for Differential Privacy Techniques in Federated Learning. Journal of Information Security, 14(02), 111–135. https://doi.org/10.4236/jis.2023.142008

Zhang, Z., Wu, T., Sun, X., & Yu, J. (2021). MPDP k -medoids: Multiple partition differential privacy preserving k -medoids clustering for data publishing in the Internet of Medical Things. International Journal of Distributed Sensor Networks, 17(10), 155014772110425. https://doi.org/10.1177/15501477211042543

Ziegler, J., Pfitzner, B., Schulz, H., Saalbach, A., & Arnrich, B. (2022a). Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data. Sensors, 22(14), 5195. https://doi.org/10.3390/s22145195

Ziegler, J., Pfitzner, B., Schulz, H., Saalbach, A., & Arnrich, B. (2022b). Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data. Sensors, 22(14), 5195. https://doi.org/10.3390/s22145195