A Credible and Fair Federated Learning Framework Based on Blockchain
Top Cited Papers
- 17 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (2) , 301-316
Abstract
Federated learning enables cooperative computation between multiple participants while protecting user privacy. Currently, federated learning algorithms assume that all participants are trustworthy and their systems are secure. However, the following problems arise in real-world scenarios: (1) Malicious clients disrupt federated learning through model poisoning and data poisoning attacks. Although some research has proposed secure aggregation methods to solve this problem, most methods have limitations. (2) Due to the variance in data quality and computational resources among participants, rewards cannot be distributed equally. Some clients also exhibit free-rider behavior, seeking to cheat the reward system and manipulate global models. Evaluating client contribution and distributing rewards also present challenges. To address these challenges, we design a trustworthy federated framework to ensure secure computing throughout the federated task process. First, we propose a malicious model detection method for secure model aggregation. Then, we also propose a fair method of assessing contribution to identify client-side free-riding behavior. Lastly, we develop a computation process grounded in blockchain and smart contracts to guarantee the trustworthiness and fairness of federated tasks. To validate the performance of our framework, we simulate different types of client attacks and contribution evaluation scenarios on several open-source datasets. The experiments show that our framework guarantees the federated task’s credibility and achieves fair client contribution evaluation.Keywords
Funding Information
- Ministry of Education - Singapore (AcRF Tier 1 RG91/22)
- China Scholarship Council (202206450035)
This publication has 29 references indexed in Scilit:
- FL-Defender: Combating targeted attacks in federated learningKnowledge-Based Systems, 2022
- Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering2022
- FGFL: A blockchain-based fair incentive governor for Federated LearningJournal of Parallel and Distributed Computing, 2022
- A Federated Parallel Data Platform for Trustworthy AI2021
- BaFFLe: Backdoor Detection via Feedback-based Federated Learning2021
- A Gamified Research Tool for Incentive Mechanism Design in Federated Learning2020
- Efficient and Fair Data Valuation for Horizontal Federated Learning2020
- Measure Contribution of Participants in Federated Learning2019
- Profit Allocation for Federated Learning2019
- Record and Reward Federated Learning Contributions with Blockchain2019