FedPoP: Federated Learning Meets Proof of Participation
By: Devriş İşler , Elina van Kempen , Seoyeon Hwang and more
Potential Business Impact:
Proves you helped train a computer model privately.
Federated learning (FL) offers privacy preserving, distributed machine learning, allowing clients to contribute to a global model without revealing their local data. As models increasingly serve as monetizable digital assets, the ability to prove participation in their training becomes essential for establishing ownership. In this paper, we address this emerging need by introducing FedPoP, a novel FL framework that allows nonlinkable proof of participation while preserving client anonymity and privacy without requiring either extensive computations or a public ledger. FedPoP is designed to seamlessly integrate with existing secure aggregation protocols to ensure compatibility with real-world FL deployments. We provide a proof of concept implementation and an empirical evaluation under realistic client dropouts. In our prototype, FedPoP introduces 0.97 seconds of per-round overhead atop securely aggregated FL and enables a client to prove its participation/contribution to a model held by a third party in 0.0612 seconds. These results indicate FedPoP is practical for real-world deployments that require auditable participation without sacrificing privacy.
Similar Papers
Zero-Knowledge Proof-Based Consensus for Blockchain-Secured Federated Learning
Distributed, Parallel, and Cluster Computing
Keeps private data safe while training AI.
Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning
Machine Learning (CS)
Protects shared computer learning from bad guys.
On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions
Cryptography and Security
Keeps shared computer learning private and safe.