FedG2L: a privacy-preserving federated learning scheme base on “G2L” against poisoning attack
Authors:
Open Access
- 6 April 2023
- journal article
- research article
- Published by Taylor & Francis in Connection Science
- Vol. 35 (1)
Abstract
Federated learning (FL) can push the limitation of “Data Island” while protecting data privacy has been a broad concern. However, the centralised FL is vulnerable to a single-point failure. While decentralised and tamper-proof blockchains can cope with the above issues, it is difficult to find a benign benchmark gradient and eliminate the poisoning attack in the later stage of global model aggregation. To address the above problems, we present a global to local based privacy-preserving federated consensus scheme against poisoning attacks (FedG2L). This scheme can effectively reduce the influence of poisoning attacks on model accuracy. In the global aggregation stage, a gradient-similarity-based secure consensus algorithm (SecPBFT) is designed to eliminate malicious gradients. During this procedure, the gradient of the data owner will not be leaked. Then, we propose an improved ACGAN algorithm to generate local data to further update the model without poisoning attacks. Finally, we theoretically prove the security and correctness of our scheme. Experimental results demonstrated that the model accuracy is improved by at least 55% than no defense scheme, and the attack success rate is reduced by more than 60%.Keywords
Funding Information
- National Natural Science Foundation of China (62125205)
- Natural Science Basic Research Plan in Shaanxi Province
This publication has 34 references indexed in Scilit:
- A decision-making framework for evaluating appropriate business blockchain platforms using multiple preference formats and VIKORInformation Sciences, 2021
- A Consortium Blockchain-Based Access Control Framework With Dynamic Orderer Node Selection for 5G-Enabled Industrial IoTIEEE Transactions on Industrial Informatics, 2021
- Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses for Federated Learning2021
- Generative adversarial networksCommunications of the ACM, 2020
- Grid-based DBSCAN: Indexing and inferencePattern Recognition, 2019
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning2018
- EMNIST: Extending MNIST to handwritten letters2017
- GRIDBSCAN: GRId Density-Based Spatial Clustering of Applications with Noise2006
- Public-Key Cryptosystems Based on Composite Degree Residuosity Classes1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998