NIDS-FGPA: A federated learning network intrusion detection algorithm based on secure aggregation of gradient similarity models
JiaMing Wang,
Kai Yang and
MinJing Li
PLOS ONE, 2024, vol. 19, issue 10, 1-33
Abstract:
With the rapid development of Industrial Internet of Things (IIoT), network security issues have become increasingly severe, making intrusion detection one of the key technologies for ensuring IIoT security. However, existing intrusion detection systems face challenges such as incomplete data features, missing labels, parameter leakage, and high communication overhead. To address these challenges, this paper proposes a federated learning-based intrusion detection algorithm (NIDS-FGPA) that utilizes gradient similarity model aggregation. This algorithm leverages a federated learning architecture and combines it with Paillier homomorphic encryption technology to ensure the security of the training process. Additionally, the paper introduces the Gradient Similarity Model Aggregation (GSA) algorithm, which dynamically selects and weights updates from different models to reduce communication overhead. Finally, the paper designs a deep learning model based on two-dimensional convolutional neural networks and bidirectional gated recurrent units (2DCNN-BIGRU) to handle incomplete data features and missing labels in network traffic data. Experimental validation on the Edge-IIoTset and CIC IoT 2023 datasets achieves accuracies of 94.5% and 99.2%, respectively. The results demonstrate that the NIDS-FGPA model possesses the ability to identify and capture complex network attacks, significantly enhancing the overall security of the network.
Date: 2024
References: Add references at CitEc
Citations:
Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0308639 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 08639&type=printable (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0308639
DOI: 10.1371/journal.pone.0308639
Access Statistics for this article
More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().