PriVeriFL: Privacy-Preserving and Aggregation-Verifiable Federated Learning
Lulu Wang, Mirko Polato, Alessandro Brighente, Mauro Conti, Lei Zhang, Lin Xu
Abstract
Federated learning provides a collaborative way to build machine learning models without sharing private data. However, attackers might infer private information from model updates submitted by participants, and the aggregator might maliciously forge the final aggregation results. Federated learning still faces data privacy and aggregation integrity challenges. In this paper, we combine inference attacks and information theory to analyze the sensitivity of different bits of model parameters. We conclude that not all bits of model parameters will leak privacy. This realization inspires us to propose a novel low-expansion homomorphic aggregation scheme based on Paillier homomorphic encryption (PHE) for safeguarding participants’ data privacy. Building upon this, we develop PriVeriFL-A, a privacy-preserving and aggregation-verifiable federated learning scheme that combines homomorphic hash function and signature. To prevent collusion attacks between the aggregator and malicious participants, we further improve our PHE-based scheme into a threshold PHE-based one, named PriVeriFL-B. Compared with the privacy-preserving federated learning scheme based on classic PHE, PriVeriFL-A reduces the communication overhead to 1.65%, and the encryption/decryption computation overhead to 0.88%. Both PriVeriFL-A and PriVeriFL-B can effectively verify the integrity of the global model, while maintaining an almost negligible communication overhead for integrity verification and protecting the privacy of participants’ data.