A novel industrial intrusion detection method based on threshold-optimized CNN-BiLSTM-attention using ROC curve

Simple item page
dc.contributor.authorLan, Mindi
dc.contributor.authorLuo, Jun
dc.contributor.authorChai, Senchun
dc.contributor.authorChai, Ruiqi
dc.contributor.authorZhang, Chen
dc.contributor.authorZhang, Baihai
dc.date.accessioned2021-06-22T14:20:09Z
dc.date.available2021-06-22T14:20:09Z
dc.date.issued2020-09-09
dc.description.abstractIn recent years, many researchers have proposed many intrusion detection methods to protect the industrial network. However, there are two existing problems among them: one is that they only consider the overall accuracy rate (AC) while ignoring the problem of class imbalance; another one is that they have considered the problem of class imbalance, but the detection rate (DR) is low and false positive rate (FR) is high for minority classes. In order to improve AC and DR of minority classes, we propose a method called threshold-optimized CNN-BiLSTM-Attention that combines CNN-BiLSTM-Attention model, with threshold modification method based on receiver operating characteristic (ROC) curve. In this method, we use CNN-BiLSTM-Attention model as a classifier and modify threshold of the classifier through ROC curve. To evaluate the proposed method, we have performed experiments on the standard industrial data set. And the experimental results show that the proposed method can improve AC and the DR of minority classes at low FR, which is better than other intrusion detection methods.en_UK
dc.identifier.citationLan M, Luo J, Chai S, et al., (2020) A novel industrial intrusion detection method based on threshold-optimized CNN-BiLSTM-attention using ROC curve. In: 2020 39th Chinese Control Conference (CCC), 27-29 July 2020, Shenyang, Chinaen_UK
dc.identifier.isbn978-1-7281-6523-3
dc.identifier.issn1934-1768
dc.identifier.urihttps://doi.org/10.23919/CCC50068.2020.9188872
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/16805
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectIndustrial intrusion detectionen_UK
dc.subjectClass imbalanceen_UK
dc.subjectCNN-BiLSTM-Attentionen_UK
dc.subjectThreshold modificationen_UK
dc.subjectROC curveen_UK
dc.titleA novel industrial intrusion detection method based on threshold-optimized CNN-BiLSTM-attention using ROC curveen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
threshold-optimized_CNN-BiLSTM-attention-2020.pdf
Size:
2.73 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)