Attack detection model for BCoT based on contrastive variational autoencoder and metric learning
Abstract With development of blockchain technology, clouding computing and Internet of Things (IoT), blockchain and cloud of things (BCoT) has become development tendency. But the security has become the most development hinder of BCoT. Attack detection model is a crucial part of attack revelation m...
Published in: | Journal of Cloud Computing |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
SpringerOpen
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1186/s13677-024-00678-w https://doaj.org/article/a3738031ff1a423bbfeaeabe72621d1b |
id |
ftdoajarticles:oai:doaj.org/article:a3738031ff1a423bbfeaeabe72621d1b |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:a3738031ff1a423bbfeaeabe72621d1b 2024-09-15T18:03:47+00:00 Attack detection model for BCoT based on contrastive variational autoencoder and metric learning Chunwang Wu Xiaolei Liu Kangyi Ding Bangzhou Xin Jiazhong Lu Jiayong Liu Cheng Huang 2024-08-01T00:00:00Z https://doi.org/10.1186/s13677-024-00678-w https://doaj.org/article/a3738031ff1a423bbfeaeabe72621d1b EN eng SpringerOpen https://doi.org/10.1186/s13677-024-00678-w https://doaj.org/toc/2192-113X doi:10.1186/s13677-024-00678-w 2192-113X https://doaj.org/article/a3738031ff1a423bbfeaeabe72621d1b Journal of Cloud Computing: Advances, Systems and Applications, Vol 13, Iss 1, Pp 1-11 (2024) Attack detection BCoT Metric learning Contrastive variational autoencoder Oversample Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95 article 2024 ftdoajarticles https://doi.org/10.1186/s13677-024-00678-w 2024-08-05T17:50:07Z Abstract With development of blockchain technology, clouding computing and Internet of Things (IoT), blockchain and cloud of things (BCoT) has become development tendency. But the security has become the most development hinder of BCoT. Attack detection model is a crucial part of attack revelation mechanism for BCoT. As a consequence, attack detection model has received more concerned. Due to the great diversity and variation of network attacks aiming to BCoT, tradition attack detection models are not suitable for BCoT. In this paper, we propose a novel attack detection model for BCoT, denoted as cVAE-DML. The novel model is based on contrastive variational autoencoder (cVAE) and deep metric learning (DML). By training the cVAE, the proposed model generates private features for attack traffic information as well as shared features between attack traffic information and normal traffic information. Based on those generated features, the proposed model can generate representative new samples to balance the training dataset. At last, the decoder of cVAE is connected to the deep metric learning network to detect attack aiming to BCoT. The efficiency of cVAE-DML is verified using the CIC-IDS 2017 dataset and CSE-CIC-IDS 2018 dataset. The results show that cVAE-DML can improve attack detection efficiency even under the condition of unbalanced samples. Article in Journal/Newspaper DML Directory of Open Access Journals: DOAJ Articles Journal of Cloud Computing 13 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Attack detection BCoT Metric learning Contrastive variational autoencoder Oversample Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
Attack detection BCoT Metric learning Contrastive variational autoencoder Oversample Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95 Chunwang Wu Xiaolei Liu Kangyi Ding Bangzhou Xin Jiazhong Lu Jiayong Liu Cheng Huang Attack detection model for BCoT based on contrastive variational autoencoder and metric learning |
topic_facet |
Attack detection BCoT Metric learning Contrastive variational autoencoder Oversample Computer engineering. Computer hardware TK7885-7895 Electronic computers. Computer science QA75.5-76.95 |
description |
Abstract With development of blockchain technology, clouding computing and Internet of Things (IoT), blockchain and cloud of things (BCoT) has become development tendency. But the security has become the most development hinder of BCoT. Attack detection model is a crucial part of attack revelation mechanism for BCoT. As a consequence, attack detection model has received more concerned. Due to the great diversity and variation of network attacks aiming to BCoT, tradition attack detection models are not suitable for BCoT. In this paper, we propose a novel attack detection model for BCoT, denoted as cVAE-DML. The novel model is based on contrastive variational autoencoder (cVAE) and deep metric learning (DML). By training the cVAE, the proposed model generates private features for attack traffic information as well as shared features between attack traffic information and normal traffic information. Based on those generated features, the proposed model can generate representative new samples to balance the training dataset. At last, the decoder of cVAE is connected to the deep metric learning network to detect attack aiming to BCoT. The efficiency of cVAE-DML is verified using the CIC-IDS 2017 dataset and CSE-CIC-IDS 2018 dataset. The results show that cVAE-DML can improve attack detection efficiency even under the condition of unbalanced samples. |
format |
Article in Journal/Newspaper |
author |
Chunwang Wu Xiaolei Liu Kangyi Ding Bangzhou Xin Jiazhong Lu Jiayong Liu Cheng Huang |
author_facet |
Chunwang Wu Xiaolei Liu Kangyi Ding Bangzhou Xin Jiazhong Lu Jiayong Liu Cheng Huang |
author_sort |
Chunwang Wu |
title |
Attack detection model for BCoT based on contrastive variational autoencoder and metric learning |
title_short |
Attack detection model for BCoT based on contrastive variational autoencoder and metric learning |
title_full |
Attack detection model for BCoT based on contrastive variational autoencoder and metric learning |
title_fullStr |
Attack detection model for BCoT based on contrastive variational autoencoder and metric learning |
title_full_unstemmed |
Attack detection model for BCoT based on contrastive variational autoencoder and metric learning |
title_sort |
attack detection model for bcot based on contrastive variational autoencoder and metric learning |
publisher |
SpringerOpen |
publishDate |
2024 |
url |
https://doi.org/10.1186/s13677-024-00678-w https://doaj.org/article/a3738031ff1a423bbfeaeabe72621d1b |
genre |
DML |
genre_facet |
DML |
op_source |
Journal of Cloud Computing: Advances, Systems and Applications, Vol 13, Iss 1, Pp 1-11 (2024) |
op_relation |
https://doi.org/10.1186/s13677-024-00678-w https://doaj.org/toc/2192-113X doi:10.1186/s13677-024-00678-w 2192-113X https://doaj.org/article/a3738031ff1a423bbfeaeabe72621d1b |
op_doi |
https://doi.org/10.1186/s13677-024-00678-w |
container_title |
Journal of Cloud Computing |
container_volume |
13 |
container_issue |
1 |
_version_ |
1810441252144939008 |