TY - JOUR
T1 - EA2-FL
T2 - An Efficient and Authentication-Aware Privacy-Preserving Protocol for Federated Learning with Client Dropout Tolerance
AU - Liu, Jianghua
AU - Yang, Jian
AU - Xia, Xiaoyu
AU - Zuo, Cong
AU - Xu, Lei
AU - Qu, Youyang
AU - Huang, Xinyi
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026/5/1
Y1 - 2026/5/1
N2 - Federated Learning (FL), an innovative distributed paradigm, has attracted significant interest for its inherent privacy preservation in collaborative model training. However, recent studies demonstrate that publicly shared gradients are vulnerable to malicious reconstruction of sensitive client data. While countermeasures like differential privacy and homomorphic encryption exist, they typically compromise model accuracy or computational efficiency, hindering practical deployment. This work simultaneously addresses two critical challenges in the FL training process: 1) efficient protection of client privacy, and 2) guaranteeing the authenticity of client gradients while ensuring the verifiability of the server's aggregation result. To this end, we propose an efficient and authentication-enhanced privacy-preserving protocol. Our solution allows clients to mask their local gradients and furnish corresponding proofs. The aggregation server subsequently verifies all submissions, aggregates only the valid masked gradients, and generates a proof for clients to verify the correctness of the aggregation result. Furthermore, the protocol is designed to be robust against client dropout. We provide formal proof that our protocol meets all security requirements in a semi-trusted environment. Both comprehensive theoretical analysis and extensive experimental evaluations confirm that our approach achieves more robust security, better dropout resilience, and superior overall efficiency compared to state-of-the-art protocols such as PSA, VerifyNet, and EVP.
AB - Federated Learning (FL), an innovative distributed paradigm, has attracted significant interest for its inherent privacy preservation in collaborative model training. However, recent studies demonstrate that publicly shared gradients are vulnerable to malicious reconstruction of sensitive client data. While countermeasures like differential privacy and homomorphic encryption exist, they typically compromise model accuracy or computational efficiency, hindering practical deployment. This work simultaneously addresses two critical challenges in the FL training process: 1) efficient protection of client privacy, and 2) guaranteeing the authenticity of client gradients while ensuring the verifiability of the server's aggregation result. To this end, we propose an efficient and authentication-enhanced privacy-preserving protocol. Our solution allows clients to mask their local gradients and furnish corresponding proofs. The aggregation server subsequently verifies all submissions, aggregates only the valid masked gradients, and generates a proof for clients to verify the correctness of the aggregation result. Furthermore, the protocol is designed to be robust against client dropout. We provide formal proof that our protocol meets all security requirements in a semi-trusted environment. Both comprehensive theoretical analysis and extensive experimental evaluations confirm that our approach achieves more robust security, better dropout resilience, and superior overall efficiency compared to state-of-the-art protocols such as PSA, VerifyNet, and EVP.
KW - Federated learning (FL)
KW - aggregation verifiability
KW - authenticity authentication
KW - privacy-preserving
UR - https://www.scopus.com/pages/publications/105029175357
U2 - 10.1109/TDSC.2026.3659330
DO - 10.1109/TDSC.2026.3659330
M3 - Article
AN - SCOPUS:105029175357
SN - 1545-5971
VL - 23
SP - 5848
EP - 5861
JO - IEEE Transactions on Dependable and Secure Computing
JF - IEEE Transactions on Dependable and Secure Computing
IS - 3
ER -