Towards Explainable Privacy Preservation in Federated Learning via Shapley Value-Guided Noise Injection
Year: 2025
Type: preprint
Abstract: This paper proposes FedSVA, an explainable differential privacy (DP) mechanism for federated learning (FL) that dynamically calibrates noise injection based on the privacy contribution of attributes via Shapley Values. Unlike heuristic DP methods, FedSVA quantifies each attribute's influence on model training and adjusts noise accordingly, providing rigorous privacy guarantees while minimizing utility loss. Theoretical analysis confirms convergence and DP properties. Experiments on CIFAR-10 and FEMNIST show state-of-the-art privacy-utility trade-offs and robust defense against reconstruction attacks.
Source: arXiv (Cornell University)
Authors: Li, Yunbo, Gui, Jiaping, Wu, Yue
Institution: Shanghai Jiao Tong University
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: 基于图网络的新型复杂网络攻击检测
OpenAlex ID: W6979323285
Cites:
Cited by:
Related to: