Citation :

Wenjuan Lian, Li Liu, Fengnian Cai, Hongbao Zhang, Xin Chen, Bin Jia, 2026. "PBDFL: A Privacy-Preserving and Byzantine-Robust Scheme for Decentralized Federated Learning" ESP International Journal of Advancements in Computational Technology (ESP-IJACT)  Volume 4, Issue 2: 01-10.

Abstract :

Federated learning (FL) effectively addresses data silos but remains vulnerable to Byzantine attacks and privacy leakage, particularly in the presence of untrusted servers. While existing robust aggregation algorithms mitigate the impact of malicious participants, accurately identifying them without compromising privacy remains a significant challenge. To address these issues, this paper proposes PBDFL, an efficient privacy-preserving and Byzantine-robust scheme for decentralized federated learning. First, we introduce a Byzantine-robust decentralized training mechanism that dynamically identifies and excludes Byzantine participants via a reputation-based system, thereby securing the global model's accuracy. Second, we design a hybrid privacy-preserving aggregation (PPA) mechanism combining Homomorphic Encryption (HE) and Differential Privacy (DP). This mechanism selectively encrypts parameters to defend against both internal inference and external eavesdropping while maintaining communication efficiency. Theoretical analysis and extensive experiments on MNIST, FashionMNIST, and EMNIST datasets demonstrate that PBDFL significantly outperforms state-of-the-art baselines. It effectively safeguards participant privacy and maintains high model accuracy even under intensive Byzantine attacks.

References :

[1] Nguyen M, Yan W Q. Temporal colour-coded facial-expression recognition using convolutional neural network[M]//International Summit Smart City 360°. Cham: Springer International Publishing, 2021: 41-54.
[2] Su Y, Huang C, Yin W, et al. Diabetes Mellitus risk prediction using age adaptation models[J]. Biomedical Signal Processing and Control, 2023, 80: 104381.
[3] Jia B, Zhang X, Liu J, et al. Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT[J]. IEEE Transactions on Industrial Informatics, 2021, 18(6): 4049-4058.
[4] Shokri R, Stronati M, Song C, et al. Membership inference attacks against machine learning models[C]//2017 IEEE symposium on security and privacy (SP). IEEE, 2017: 3-18.
[5] Song C, Ristenpart T, Shmatikov V. Machine learning models that remember too much[C]//Proceedings of the 2017 ACM SIGSAC Conference on computer and communications security. 2017: 587-601.
[6] Dwork C, Roth A. The algorithmic foundations of differential privacy[J]. Foundations and trends® in theoretical computer science, 2014, 9(3-4): 211-487.
[7] Ku H, Susilo W, Zhang Y, et al. Privacy-preserving federated learning in medical diagnosis with homomorphic re-encryption[J]. Computer Standards & Interfaces, 2022, 80: 103583.
[8] Zeng Y, Lin Y, Yang Y, et al. Differentially private federated temporal difference learning[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 33(11): 2714-2726.
[9] Lian W, Zhang Y, Chen X, et al. IPCADP‐Equalizer: An Improved Multibalance Privacy Preservation Scheme against Backdoor Attacks in Federated Learning[J]. International Journal of Intelligent Systems, 2023, 2023(1): 6357750.
[10] Truex S, Liu L, Chow K H, et al. LDP-Fed: Federated learning with local differential privacy[C]//Proceedings of the third ACM international workshop on edge systems, analytics and networking. 2020: 61-66.
[11] Xu G, Li H, Zhang Y, et al. Privacy-preserving federated deep learning with irregular users[J]. IEEE Transactions on Dependable and Secure Computing, 2020, 19(2): 1364-1381.
[12] Aono Y, Hayashi T, Wang L, et al. Privacy-preserving deep learning via additively homomorphic encryption[J]. IEEE transactions on information forensics and security, 2017, 13(5): 1333-1345.
[13] Yuan K, Wu Z, Ling Q. A Byzantine-resilient dual subgradient method for vertical federated learning[C]//ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022: 4273-4277.
[14] Blanchard P, El Mhamdi E M, Guerraoui R, et al. Machine learning with adversaries: Byzantine tolerant gradient descent[J]. Advances in neural information processing systems, 2017, 30.
[15] Xie C, Koyejo O, Gupta I. Zeno: Byzantine-suspicious stochastic gradient descent[J]. arXiv preprint arXiv:1805.10032, 2018, 24.
[16] Chen Y, Su L, Xu J. Distributed statistical machine learning in adversarial settings: Byzantine gradient descent[J]. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2017, 1(2): 1-25.
[17] Shokri R, Shmatikov V. Privacy-preserving deep learning[C]//Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 2015: 1310-1321.
[18] Hamm J, Cao Y, Belkin M. Learning privately from multiparty data[C]//International Conference on Machine Learning. PMLR, 2016: 555-563.
[19] Li Y, Li H, Xu G, et al. Efficient privacy-preserving federated learning with unreliable users[J]. IEEE Internet of Things Journal, 2021, 9(13): 11590-11603.
[20] Yang Q, Liu Y, Chen T, et al. Federated machine learning: Concept and applications[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2019, 10(2): 1-19.
[21] L. Li, W. Xu, T. Chen, G. B. Giannakis, Q. Ling, RSA: byzantine-robust stochastic aggregation methods for distributed learning from heterogeneous datasets, in: Proceedings of the AAAI Conference on Artificial Intelligence,2019, pp. 1544–1551.
[22] Cao, X., Jia, J., & Gong, N. Z. (2021). Provably Secure Federated Learning against Malicious Clients. Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), 6885-6893. https://doi.org/10.1609/aaai.v35i8.16849
[23] Ma X, Zhou Y, Wang L, et al. Privacy-preserving Byzantine-robust federated learning[J]. Computer Standards & Interfaces, 2022, 80: 103561.
[24] Zhao L, Jiang J, Feng B, et al. Sear: Secure and efficient aggregation for byzantine-robust federated learning[J]. IEEE Transactions on Dependable and Secure Computing, 2021, 19(5): 3329-3342.
[25] Hu C, Jiang J, Wang Z. Decentralized federated learning: A segmented gossip approach[J]. arXiv preprint arXiv:1908.07782, 2019.
[26] Hegedűs, I., Danner, G., Jelasity, M. (2019). Gossip Learning as a Decentralized Alternative to Federated Learning. In: Pereira, J., Ricci, L. (eds) Distributed Applications and Interoperable Systems. DAIS 2019. Lecture Notes in Computer Science(), vol 11534. Springer, Cham. https://doi.org/10.1007/978-3-030-22496-7_5
[27] Zhao J, Zhu H, Wang F, et al. PVD-FL: A privacy-preserving and verifiable decentralized federated learning framework[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 2059-2073.
[28] Che C, Li X, Chen C, et al. A decentralized federated learning framework via committee mechanism with convergence guarantee[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(12): 4783-4800.
[29] Cheon, J.H., Kim, A., Kim, M., Song, Y. (2017). Homomorphic Encryption for Arithmetic of Approximate Numbers. In: Takagi, T., Peyrin, T. (eds) Advances in Cryptology – ASIACRYPT 2017. ASIACRYPT 2017. Lecture Notes in Computer Science(), vol 10624. Springer, Cham. https://doi.org/10.1007/978-3-319-70694-8_15
[30] Ou W, Zeng J, Guo Z, et al. A homomorphic-encryption-based vertical federated learning scheme for rick management. Computer Science and Information Systems, 2020, 17(3): 819−834
[31] Tian H, Zeng C, Ren Z, et al. Sphinx: Enabling privacy-preserving online learning over the cloud[C]//2022 IEEE Symposium on Security and Privacy (SP). IEEE, 2022: 2487-2501.
[32] Truex S, Baracaldo N, Anwar A, et al. A hybrid approach to privacy-preserving federated learning[C]//Proceedings of the 12th ACM workshop on artificial intelligence and security. 2019: 1-11.
[33] Ma X, Sun X, Wu Y, et al. Differentially private byzantine-robust federated learning[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(12): 3690-3701.

Keywords :

Federated Learning, Byzantine Robustness, Decentralized Architecture, Privacy-Preserving Aggregation, Homomorphic Encryption.