Blockchain-based Federated Learning Utilizing Zero-Knowledge Proofs for Verifiable Training and Aggregation
Authors:
- 19 August 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 54-63
Abstract
Federated learning is a distributed learning technique that enables parties to train a model collaboratively without disclosing their local data. To this end, a centralized aggregator collects local models from participating parties and aggregates them to form a global model. However, if parties are malicious, this approach is susceptible to security threats such as model poisoning and global aggregation attacks. Blockchain-based federated learning has been introduced as an alternative to the centralized aggregator to aggregate local models directly on the blockchain. However, employing blockchain-based solutions introduces challenges, including high computational costs and privacy concerns. To mitigate such challenges, this paper leverages zero-knowledge proofs (i.e., zk-SNARKs) to guarantee the privacy and verifiability of local model training and global model aggregation. The proposed framework verifies the local and global models' computational correctness without storing and revealing them on the blockchain. We evaluate our framework by utilizing a real-life dataset, with experimental results demonstrating its viability regarding both computational costs and learning model performance.Keywords
This publication has 24 references indexed in Scilit:
- Blockchain-based privacy-preserving multi-tasks federated learning frameworkConnection Science, 2024
- Federify: A Verifiable Federated Learning Scheme Based on zkSNARKs and BlockchainIEEE Access, 2023
- BV-ICVs: A privacy-preserving and verifiable federated learning framework for V2X environments using blockchain and zkSNARKsJournal of King Saud University Computer and Information Sciences, 2023
- Securing federated learning with blockchain: a systematic literature reviewArtificial Intelligence Review, 2022
- Survey on federated learning threats: Concepts, taxonomy on attacks and defences, experimental study and challengesInformation Fusion, 2022
- Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issuesCluster Computing, 2022
- A survey on security and privacy of federated learningFuture Generation Computer Systems, 2021
- On the Size of Pairing-Based Non-interactive Arguments2016
- Definitions and properties of zero-knowledge proof systemsJournal of Cryptology, 1994
- Feed-forward neural networksIEEE Potentials, 1994