FAST: Adopting Federated Unlearning to Eliminating Malicious Terminals at Server Side
Xintong Guo, Pengfei Wang, Sen Qiu, Wei Song, Qiang Zhang, Xiaopeng Wei, Dongsheng Zhou
Abstract
The emergence of the right to be forgotten has sparked interest in federated unlearning. Researchers utilize federated unlearning to address the issue of removing user contributions. However, practical implementation is challenging when malicious clients are involved. In this paper, we propose FAST, i.e., Adopting <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</u> ederated unle <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</u> rning to Eliminating Maliciou <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</u> <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</u> erminals at Server Side, a framework with three main components: 1) eliminating contributions of malicious clients: the central server records and subtracts updates of malicious clients from the global model, 2) judging unlearning efficiency: we model a mechanism to assess unlearning efficiency and prevent over-unlearning, and 3) remedying unlearning model performance: the central server utilizes a benchmark dataset to remedy model bias during unlearning. Experimental results demonstrate that FAST can achieve 96.98% accuracy on the MNIST dataset with 40% malicious clients, offering a 16x speedup to retraining from scratch. Meanwhile, it can recover model utility with high efficiency, and extensive evaluations of four real-world datasets demonstrate the validity of our proposed scheme.