Open access
2026
Privacy-Preserving and Byzantine-Robust Federated Learning With Mean-Constrained Secret Sharing
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.
Guang-Ye Zhu, Liqiang Wu, Ke-Qian Liu
· IEEE Access · 0 citations