FLRAM: Robust Aggregation Technique for Defense against Byzantine Poisoning Attacks in Federated Learning
Electronics · 2023-10-30 · 12 (21) · 4463
DOI: 10.3390/electronics12214463 ↗At a glance
Journal article in Electronics, published online on 2023-10-30. Written by Haitian Chen and 3 co-authors. Cited 21 times so far (Crossref); 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China.
Abstract (original language)
In response to the susceptibility of federated learning, which is based on a distributed training structure, to byzantine poisoning attacks from malicious clients, resulting in issues such as slowed or disrupted model convergence and reduced model accuracy, we propose a robust aggregation technique for defending against byzantine poisoning attacks in federated learning, known as FLRAM. First, we employ isolation forest and an improved density-based clustering algorithm to detect anomalies in the amplitudes and symbols of client local gradients, effectively filtering out gradients with large magnitude and angular deviation variations. Subsequently, we construct a credibility matrix based on the filtered subset of gradients to evaluate the trustworthiness of each local gradient. Using this credibility score, we further select gradients with higher trustworthiness. Finally, we aggregate the filtered gradients to obtain the global gradient, which is then used to update the global model. The experimental findings show that our proposed approach achieves strong defense performance without compromising FedAvg accuracy. Furthermore, it exhibits superior robustness compared to existing solutions.
Funding
- National Natural Science Foundation of China
Cite
APA
Chen, H., Chen, X., Peng, L., & Ma, R. (2023). FLRAM: Robust Aggregation Technique for Defense against Byzantine Poisoning Attacks in Federated Learning. Electronics, 12(21), 4463. https://doi.org/10.3390/electronics12214463
Vancouver
Chen H, Chen X, Peng L, Ma R. FLRAM: Robust Aggregation Technique for Defense against Byzantine Poisoning Attacks in Federated Learning. Electronics. 2023;12(21):4463. doi:10.3390/electronics12214463
BibTeX
@article{Chen2023,
author = {Chen, Haitian and Chen, Xuebin and Peng, Lulu and Ma, Ruikui},
title = {FLRAM: Robust Aggregation Technique for Defense against Byzantine Poisoning Attacks in Federated Learning},
journal = {Electronics},
year = {2023},
volume = {12},
number = {21},
pages = {4463},
doi = {10.3390/electronics12214463}
}
EUVIMED