InfoResearchPeer-reviewed
Unveiling Privacy Risks in Federated Learning: An Efficient Bias-Based Membership Inference Attack and Adaptive Defense
- Published
- Record updated
Summary
Researchers show that bias parameters in deep neural networks make federated learning vulnerable to membership inference attacks, which reveal whether a data point was in the training set. They build efficient bias-based attacks for both a local participant and the central server, using a shallow neural network and a difference-comparison step to identify the source participant. Experiments on four public datasets report higher accuracy than prior methods and robustness against common defenses.
Mitigation
They introduce an adaptive noise pruning defense (ANPD) that mitigates the bias-based membership inference attack without substantially degrading target model performance.
Topics
Related items
- InfoAudioTrace: File-Level Membership Detection for Audio Large Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoInvestigating differentially private learning for document key information extractionSimilar attack · OpenAlex (peer-reviewed AI security)
- InfoA Systematic Review of Privacy-Preserving Approaches in Deep Learning ApplicationsSimilar attack · OpenAlex (peer-reviewed AI security)
- InfoCoRTeC: A Differentially Private Release for Synthetic Tabular Data, Decodable by Any GeneratorSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoTiming is Everything: Inferring Temporal Membership in Continually Updated ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)