The first paper, "Blockchain-Based Federated Learning Utilizing Zero-Knowledge Proofs for Verifiable Training and Aggregation," tackles the challenges in federated learning. This approach leverages zero-knowledge proofs and blockchain technology to ensure the privacy and verifiability of model training and aggregation without a centralized aggregator. Our experimental results demonstrate its efficiency and effectiveness in maintaining data integrity and security.
The second paper, "zkSSI: A Zero-Knowledge-Based Self-Sovereign Identity Framework," presents zkSSI, a novel framework for digital identity management. This solution utilizes zk-SNARKs to allow verifiers to express complex conditions and verify compliance while ensuring user privacy. The framework is designed to operate efficiently in both on-chain and off-chain environments, even with consumer-grade hardware.
These papers represent significant advancements in federated learning and identity management, showcasing the potential of blockchain and zero-knowledge proofs to address critical security and privacy challenges.
We look forward to presenting our findings and engaging with the global blockchain community at IEEE Blockchain 2024.
