ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated Learning

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 crafts malicious local gradients to harm the accuracy of the federated model. To resist model poisoning attacks, existing defense strategies focus on identifying suspicious local gradients over plaintexts. However, the Byzantine adversary submits encrypted poisonous gradients to circumvent existing defense strategies in PPFL, resulting in encrypted model poisoning. To address the issue, in this paper we design a…

• NN
  National Natural Science Foundation of China

  Awards: U1804263, 62072352, 62121001, 62072361
• NK
  National Key Research and Development Program of China

  Award: 2021YFB3101100
• FR
  Fundamental Research Funds for the Central Universities

  Award: JB211505
• KR
  Key Research and Development Projects of Shaanxi Province

  Awards: 2019ZDLGY12-04, 2020ZDLGY09-06