Cargando…

Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction

The log messages generated in the system reflect the state of the system at all times. The realization of autonomous detection of abnormalities in log messages can help operators find abnormalities in time and provide a basis for analyzing the causes of abnormalities. First, this paper proposes a lo...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Qiaozheng, Zhang, Xiuguo, Wang, Xuejie, Cao, Zhiying
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774910/
https://www.ncbi.nlm.nih.gov/pubmed/35052095
http://dx.doi.org/10.3390/e24010069
_version_ 1784636456371748864
author Wang, Qiaozheng
Zhang, Xiuguo
Wang, Xuejie
Cao, Zhiying
author_facet Wang, Qiaozheng
Zhang, Xiuguo
Wang, Xuejie
Cao, Zhiying
author_sort Wang, Qiaozheng
collection PubMed
description The log messages generated in the system reflect the state of the system at all times. The realization of autonomous detection of abnormalities in log messages can help operators find abnormalities in time and provide a basis for analyzing the causes of abnormalities. First, this paper proposes a log sequence anomaly detection method based on contrastive adversarial training and dual feature extraction. This method uses BERT (Bidirectional Encoder Representations from Transformers) and VAE (Variational Auto-Encoder) to extract the semantic features and statistical features of the log sequence, respectively, and the dual features are combined to perform anomaly detection on the log sequence, with a novel contrastive adversarial training method also used to train the model. In addition, this paper introduces the method of obtaining statistical features of log sequence and the method of combining semantic features with statistical features. Furthermore, the specific process of contrastive adversarial training is described. Finally, an experimental comparison is carried out, and the experimental results show that the method in this paper is better than the contrasted log sequence anomaly detection method.
format Online
Article
Text
id pubmed-8774910
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87749102022-01-21 Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction Wang, Qiaozheng Zhang, Xiuguo Wang, Xuejie Cao, Zhiying Entropy (Basel) Article The log messages generated in the system reflect the state of the system at all times. The realization of autonomous detection of abnormalities in log messages can help operators find abnormalities in time and provide a basis for analyzing the causes of abnormalities. First, this paper proposes a log sequence anomaly detection method based on contrastive adversarial training and dual feature extraction. This method uses BERT (Bidirectional Encoder Representations from Transformers) and VAE (Variational Auto-Encoder) to extract the semantic features and statistical features of the log sequence, respectively, and the dual features are combined to perform anomaly detection on the log sequence, with a novel contrastive adversarial training method also used to train the model. In addition, this paper introduces the method of obtaining statistical features of log sequence and the method of combining semantic features with statistical features. Furthermore, the specific process of contrastive adversarial training is described. Finally, an experimental comparison is carried out, and the experimental results show that the method in this paper is better than the contrasted log sequence anomaly detection method. MDPI 2021-12-30 /pmc/articles/PMC8774910/ /pubmed/35052095 http://dx.doi.org/10.3390/e24010069 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Qiaozheng
Zhang, Xiuguo
Wang, Xuejie
Cao, Zhiying
Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction
title Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction
title_full Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction
title_fullStr Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction
title_full_unstemmed Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction
title_short Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction
title_sort log sequence anomaly detection method based on contrastive adversarial training and dual feature extraction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774910/
https://www.ncbi.nlm.nih.gov/pubmed/35052095
http://dx.doi.org/10.3390/e24010069
work_keys_str_mv AT wangqiaozheng logsequenceanomalydetectionmethodbasedoncontrastiveadversarialtraininganddualfeatureextraction
AT zhangxiuguo logsequenceanomalydetectionmethodbasedoncontrastiveadversarialtraininganddualfeatureextraction
AT wangxuejie logsequenceanomalydetectionmethodbasedoncontrastiveadversarialtraininganddualfeatureextraction
AT caozhiying logsequenceanomalydetectionmethodbasedoncontrastiveadversarialtraininganddualfeatureextraction