Publicly Verifiable and Fault-Tolerant Privacy-Preserving Aggregation for Federated Learning
Abstract
Publicly verifiable privacy-preserving aggregation is widely regarded as an effective approach to protect user privacy and ensure the integrity of the aggregated model published by the aggregator in Federated Learning (FL). State-of-the-art solutions either fail to guarantee unforgeability when the aggregator colludes with malicious users or require costly cryptographic operations during the online aggregation phase and lack fault tolerance. In this work, we propose eVTPA, the first online-efficient, publicly verifiable, and fault-tolerant privacy-preserving aggregation protocol considering malicious users and aggregators for FL. We introduce a novel collusion-resistant symmetric masking technique to conceal users' local gradients while ensuring the correctness of the aggregated model through a publicly verifiable aggregation signature algorithm. To improve the efficiency of online signature generation, we design a specialized precomputation-based acceleration method and leverage the randomness of masking to enable batch processing. Furthermore, eVTPA adopts a dynamic mask update mechanism that tolerates user dropouts without affecting the validation of the aggregated model. Security analysis shows that eVTPA meets FL's confidentiality, integrity, and authenticity requirements. Experimental results demonstrate that our scheme maintains model classification accuracy while achieving at least a 7.85× faster online aggregation than related solutions at the same security level.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.