MemberShield: A framework for federated learning with membership privacy
Year: 2024
Type: article
Abstract: Federated Learning (FL) allows multiple data owners to build high-quality deep learning models collaboratively, by sharing only model updates and keeping data on their premises. Even though FL offers privacy-by-design, it is vulnerable to membership inference attacks (MIA), where an adversary tries to determine whether a sample was included in the training data. Existing defenses against MIA cannot offer meaningful privacy protection without significantly hampering the model's utility and causing a non-negligible training overhead. In this paper we analyze the underlying causes of the differences in the model behavior for member and non-member samples, which arise from model overfitting and facilitate MIAs. Accordingly, we propose MemberShield, a generalization-based defense method for MIAs that consists of: (i) one-time preprocessing of each client's training data labels that transforms one-hot encoded labels to soft labels and eventually exploits them in local training, and (ii) early stopping the training when the local model's validation accuracy does not improve on that of the global model for a number of epochs. Extensive empirical evaluations on three widely used datasets and four model architectures demonstrate that MemberShield outperforms state-of-the-art defense methods by delivering substantially better practical privacy protection against all forms of MIAs, while better preserving the target model utility. On top of that, our proposal significantly reduces training time and is straightforward to implement, by just tuning a single hyperparameter.
Source: Neural Networks
Authors: Faisal Ahmed, David Sánchez, Zouhair Haddi, Josep Domingo-Ferrer
Institution: Universitat Rovira i Virgili
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,350
Funders: European Commission, Generalitat de Catalunya, Institució Catalana de Recerca i Estudis Avançats, Ministerio de Ciencia e Innovación, Instituto Nacional de Ciberseguridad, Horizon 2020 Framework Programme, European Regional Development Fund, Agencia Estatal de Investigación, NextGenerationEU
OpenAlex ID: W4403015767