${\sf FedRLChain}$: Secure Federated Deep Reinforcement Learning With Blockchain
- 11 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 16 (6) , 3865-3878
Abstract
This paper introduces ${\sf FedRLChain}$ , a novel framework for blockchain-based secure federated deep reinforcement learning, which allows users to securely and collaboratively train a Deep Reinforcement Learning (DRL) model by plugging appropriate aggregation and verification algorithms for specific problems. Unlike existing systems, ${\sf FedRLChain}$ adopts (1) a novel verification algorithm to prevent malicious clients, (2) an aggregation weight scheme from preventing the global model from getting biased toward any client, and (3) a variant of traditional FedAverage algorithm to accelerate the convergence process. We perform a rigorous experimental evaluation of ${\sf FedRLChain}$ considering the classic cart-pole problem, and we show a significant improvement in the number of epochs and time required for model convergence w.r.t. the state-of-the-art frameworks – DDQL, BAFFLE, and BASE-PIoT.Keywords
Funding Information
- Meity NIC, Government of India (B-13011/1/2022-Training/3134963)
This publication has 12 references indexed in Scilit:
- FedCrowd: A Federated and Privacy-Preserving Crowdsourcing Platform on BlockchainIEEE Transactions on Services Computing, 2022
- Blockchain and Federated Deep Reinforcement Learning Based Secure Cloud-Edge-End Collaboration in Power IoTIEEE Wireless Communications, 2022
- BlockFLA2021
- Biscotti: A Blockchain System for Private and Secure Federated LearningIEEE Transactions on Parallel and Distributed Systems, 2020
- ESync: Accelerating Intra-Domain Federated Learning in Heterogeneous Data CentersIEEE Transactions on Services Computing, 2020
- BAFFLE : Blockchain Based Aggregator Free Federated Learning2020
- DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-based IncentiveIEEE Transactions on Dependable and Secure Computing, 2019
- A Survey of Blockchain From the Perspectives of Applications, Challenges, and OpportunitiesIEEE Access, 2019
- Human-level control through deep reinforcement learningNature, 2015
- The Byzantine Generals ProblemACM Transactions on Programming Languages and Systems, 1982