{"title":"An IIoT Temporal Data Anomaly Detection Method Combining Transformer and Adversarial Training","authors":"Yuan Tian, Wendong Wang, Jingyuan He","doi":"10.4018/ijisp.343306","DOIUrl":null,"url":null,"abstract":"The existing Industrial Internet of Things (IIoT) temporal data analysis methods often suffer from issues such as information loss, difficulty balancing spatial and temporal features, and being affected by training data noise, which can lead to varying degrees of reduced model accuracy. Therefore, a new anomaly detection method was proposed, which integrated Transformer and adversarial training. Firstly, a bidirectional spatiotemporal feature extraction module was constructed by combining Graph Attention Networks (GAT) and Bidirectional Gated Recurrent Unit (BiGRU), which can simultaneously extract spatial and temporal features. Then, by combining multi-scale convolution with Long Short-Term Memory (LSTM), multi-scale contextual information was captured. Finally, an improved Transformer was used to fuse multi-dimensional features, combined with an adversarial-trained variational autoencoder to calculate the anomalies of the input data. This method outperforms other comparison models by conducting experiments on four publicly available datasets.","PeriodicalId":44332,"journal":{"name":"International Journal of Information Security and Privacy","volume":null,"pages":null},"PeriodicalIF":0.5000,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Information Security and Privacy","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijisp.343306","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
The existing Industrial Internet of Things (IIoT) temporal data analysis methods often suffer from issues such as information loss, difficulty balancing spatial and temporal features, and being affected by training data noise, which can lead to varying degrees of reduced model accuracy. Therefore, a new anomaly detection method was proposed, which integrated Transformer and adversarial training. Firstly, a bidirectional spatiotemporal feature extraction module was constructed by combining Graph Attention Networks (GAT) and Bidirectional Gated Recurrent Unit (BiGRU), which can simultaneously extract spatial and temporal features. Then, by combining multi-scale convolution with Long Short-Term Memory (LSTM), multi-scale contextual information was captured. Finally, an improved Transformer was used to fuse multi-dimensional features, combined with an adversarial-trained variational autoencoder to calculate the anomalies of the input data. This method outperforms other comparison models by conducting experiments on four publicly available datasets.
期刊介绍:
As information technology and the Internet become more and more ubiquitous and pervasive in our daily lives, there is an essential need for a more thorough understanding of information security and privacy issues and concerns. The International Journal of Information Security and Privacy (IJISP) creates and fosters a forum where research in the theory and practice of information security and privacy is advanced. IJISP publishes high quality papers dealing with a wide range of issues, ranging from technical, legal, regulatory, organizational, managerial, cultural, ethical and human aspects of information security and privacy, through a balanced mix of theoretical and empirical research articles, case studies, book reviews, tutorials, and editorials. This journal encourages submission of manuscripts that present research frameworks, methods, methodologies, theory development and validation, case studies, simulation results and analysis, technological architectures, infrastructure issues in design, and implementation and maintenance of secure and privacy preserving initiatives.