RFed: Robustness-Enhanced Privacy-Preserving Federated Learning against poisoning attack

• Main Authors: MIAO, Yinbin, YAN, Xinru, LI, Xinghua, XU, Shujiang, LIU, Ximeng, LI, Hongwei, DENG, Robert H.
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Computational modeling; Federated learning; poisoning attack; Privacy; privacy protection; Robustness; scaled dot-product attention mechanism; Security; Servers; Training; Information Security
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8817

Federated learning not only realizes collaborative training of models, but also effectively maintains user privacy. However, with the widespread application of privacy-preserving federated learning, poisoning attacks threaten the model utility. Existing defense schemes suffer from a series of proble...