Skip to content
Open access

Privacy-Preserving and Byzantine-Robust Federated Learning With Mean-Constrained Secret Sharing

2026 · IEEE Access · Vol 14, pp. 136675-136693 · 0 citations · 33 references

TL;DR

PVeriFL is a federated learning framework that integrates privacy preservation, Byzantine fault tolerance, and lightweight client-side verifiability and effectively unifies the three security objectives, offering a practical and trustworthy solution for real-world federated learning systems.

Abstract

Federated learning faces three critical challenges in enabling cross-institutional collaboration: privacy leakage, poisoning by malicious clients, and unverifiable aggregation results. To address these issues in a unified manner, we propose PVeriFL—a federated learning framework that integrates privacy preservation, Byzantine fault tolerance, and lightweight client-side verifiability. Its core innovation is a dynamic mean-constrained secret sharing (DMCSS) mechanism. By imposing quantile-based constraints, DMCSS ensures that secret shares closely follow the directional profile of the original gradients. This enables robust gradient filtering while maintaining strong privacy guarantees. Building on DMCSS, we design an efficient two-server protocol that securely performs Top- $k$ filtering on encrypted shares. Clients can then non-interactively verify the correctness of aggregated results using homomorphic hashing. Theoretical analysis proves the security of PVeriFL and formally quantifies the inherent privacy–robustness trade-off. Comprehensive experiments on multiple datasets show that under 50% client poisoning, PVeriFL achieves accuracy comparable to the state-of-the-art scheme P2Brofl (e.g., 96.71% on MNIST) while delivering major efficiency gains: end-to-end runtime is reduced to 34.7% of P2Brofl, computational overhead drops to about 2.25%, and communication overhead is lowered by 25%. PVeriFL thus effectively unifies the three security objectives, offering a practical and trustworthy solution for real-world federated learning systems.

Read PDF

Similar papers

Open access Aug 2026

DMSA-FL: secure and robust federated learning via double-masked secure aggregation with multiparty homomorphic encryption

This paper proposes DMSA-FL as a practical and robust FL framework leveraging double-masked secure aggregation integrated with multiparty homomorphic encryption, and designs a strategy that encrypts only low-dimensional mask seeds rather than high-dimensional gradients.

Wen-Hao Liu, Xu-An Wang, Wei-Wei Jiang et al. · 0 citations

PNFR: practicality-enhanced and non-interactive privacy-preserving federated regressions

PNFR is designed, a privacy-preserving federated learning scheme for regressions training built on the MPaillier algorithm, which is three times faster than interactive federated regressions PrivFL and about 80% faster than non-interactive federated regressions VANE.

Hui-Yu Xie, Tan-Ping Zhou, Shuo Chen et al. · 0 citations
2026

Differential Privacy Enabled Cascaded Filter for Efficient and Privacy-Preserving Federated Learning

Federated learning (FL) enables collaborative model training across multiple clients in a privacy-preserving manner. However, the employment of homomorphic encryption algorithms might lead to high computational cost while the application of differential privacy (DP) methods would sacrifice model performance. To establi...

Zhiqiang Chen, Yuchen Jiang, Ray Y. Zhong et al. · 0 citations
#federated learning Open access Sep 2026

Trustworthy and privacy-preserving decentralized federated learning with multi-layer defense for secure collaborative AI

These findings demonstrate that the proposed framework provides an effective balance between privacy preservation, adversarial robustness, and trustworthy decentralized collaborative learning for secure AI-driven systems.

Durga Sivan, Uma Maheshwari Shanmugam, Sachnev Vasily et al. · 0 citations
Preprint Oct 2026

Combining Homomorphic Encryption and Differential Privacy in Federated Learning for Model Inspection and Availability

The increasing prevalence of decentralized data has led to a growing interest in federated learning, which enables collaborative model training without clients sharing their sensitive local data. However, FL alone does not sufficiently protect sensitive training data and is generally coupled with privacy-preserving tec...

Ceren Yildirim, K. Kaya, S. Yıldırım et al. · 0 citations
#federated learning Open access Sep 2026

A Privacy-Preserving Distributed Machine Learning Aggregation Scheme

A multi-server secure aggregation scheme based on additive secret sharing that achieves information-theoretic privacy protection, effectively breaking the trilemma among privacy, accuracy, and efficiency.

Ming-Yuan Li · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.