Mitigating Data Reconstruction Attacks in Federated Learning: Conditions, Bounds, and Theoretical Guarantees

Abstract:Privacy attacks, particularly data reconstruction attacks, pose significant challenges to federated learning despite its promise in privacy-preserving collaborative training. This paper presents a comprehensive theoretical analysis of privacy leakage in federated learning through dual perspectives: linear algebra and optimization theory. By analyzing the client-update Jacobian, we identify conditions under which distinct data batches produce the same model update and derive a sufficient batch-size criterion for non-unique reconstruction. Through optimization theory, we establish a novel upper bound for privacy leakage that incorporates batch size, distortion extent, and other critical parameters. These theoretical insights elucidate the fundamental relationships between system parameters and privacy vulnerability, laying the groundwork for developing more robust privacy-preserving federated learning frameworks.

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)

arXiv:2407.16735 [cs.CR]

(or arXiv:2407.16735v2 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2407.16735 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.