ShieldFL: Mitigating model poisoning attacks in privacy-preserving federated learning

• Main Authors: MA, Zhuoran, MA, Jianfeng, MIAO, Yinbin, LI, Yingjiu, DENG, Robert H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Cryptography; Data models; Privacy; Computational modeling; Servers; Data privacy; Homomorphic encryption; Privacy-preserving; homomorphic encryption; defense strategy; model poisoning attack; federated learning; Databases and Information Systems; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/7252; https://doi.org/10.1109/TIFS.2022.3169918
• Institution: Singapore Management University

Privacy-Preserving Federated Learning (PPFL) is an emerging secure distributed learning paradigm that aggregates user-trained local gradients into a federated model through a cryptographic protocol. Unfortunately, PPFL is vulnerable to model poisoning attacks launched by a Byzantine adversary, who c...