Towards Explainable Privacy Preservation in Federated Learning via Shapley Value-Guided Noise Injection
This addresses privacy preservation in federated learning for applications like image classification, though it is incremental as it builds on existing DP methods with a novel calibration approach.
The paper tackles the problem of balancing privacy and utility in federated learning by proposing FedSVA, an explainable differential privacy mechanism that uses Shapley Values to guide noise injection, achieving state-of-the-art privacy-utility trade-offs on datasets like CIFAR-10 and FEMNIST.
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.