FedPoP: Federated Learning Meets Proof of Participation

2025-11-11

AI Summary

In federated learning, ensuring verifiable client contributions while preserving privacy remains challenging. Method: This paper proposes a lightweight, unlinkable proof-of-participation framework that integrates cryptographic signatures with lightweight zero-knowledge proofs into the secure aggregation pipeline—eliminating reliance on public ledgers or trusted third parties. The framework enables anonymous, verifiable attribution of contributions to the global model without revealing client identities or local data. It is compatible with mainstream secure aggregation protocols and incurs only 0.97 seconds of overhead per training round, with clients generating proofs in just 0.0612 seconds. Results: Experiments demonstrate robust performance under realistic intermittent connectivity, maintaining efficiency and stability. The approach significantly enhances practicality and regulatory compliance of federated learning in audit-sensitive domains such as healthcare and finance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Safety and Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

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.

Problem

• Enabling verifiable participation proof in federated learning systems
• Preserving client anonymity while proving model contribution
• Providing auditable participation without computational overhead

Innovation

• Federated Learning with nonlinkable proof of participation
• Preserves client anonymity without public ledger
• Seamlessly integrates with secure aggregation protocols