Guaranteeing data privacy in federated unlearning with dynamic user participation

• Main Authors: Liu, Ziyao, Jiang, Yu, Jiang, Weifeng, Guo, Jiale, Zhao, Jun, Lam, Kwok-Yan
• Other Authors: College of Computing and Data Science
• Format: Article
• Language: English
• Published: 2025
• Subjects: Computer and Information Science; AI safety; Digital trust
• Online Access: https://hdl.handle.net/10356/182940
• Institution: Nanyang Technological University

Federated Unlearning (FU) is gaining prominence for its capability to eliminate influences of specific users' data from trained global Federated Learning (FL) models. A straightforward FU method involves removing the unlearned user-specified data and subsequently obtaining a new global FL model...