IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model
The Internet of Things (IoT) is increasingly providing industrial production objects to connect with the physical world and has been widely used in various fields. Although it has brought great industrial convenience, there are also potential security threats due to the vulnerabilities and malicious...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/20/3287 |
| _version_ | 1797473676965183488 |
|---|---|
| author | Yunyun Hou Ruiyu He Jie Dong Yangrui Yang Wei Ma |
| author_facet | Yunyun Hou Ruiyu He Jie Dong Yangrui Yang Wei Ma |
| author_sort | Yunyun Hou |
| collection | DOAJ |
| description | The Internet of Things (IoT) is increasingly providing industrial production objects to connect with the physical world and has been widely used in various fields. Although it has brought great industrial convenience, there are also potential security threats due to the vulnerabilities and malicious nodes in IoT. To correctly identify the traffic of malicious nodes in IoT and reduce the damage caused by malicious attacks on IoT devices, this paper proposes an autoencoder-based IoT malicious node detection method. The contributions of this paper are as follows: firstly, the high complexity multi-featured traffic data are processed and dimensionally reduced through the autoencoder to obtain the low-dimensional feature data. Then, the Bayesian Gaussian mixture model is adopted to cluster the data in a low-dimensional space to detect anomalies. Furthermore, the method of variational inference is used to estimate the parameters in the Bayesian Gaussian mixture model. To evaluate our model’s effectiveness, we used a public dataset for our experiments. As a result, in the experiment, the proposed method achieves a high accuracy rate of 99% distinguishing normal and abnormal traffic with three-dimension data reduced by the autoencoder, and it establishes our model’s better detection performance compared with previous K-means and Gaussian Mixture Model (GMM) solutions. |
| first_indexed | 2024-03-09T20:19:48Z |
| format | Article |
| id | doaj.art-c8991e85190141a8a5526d7d743e134c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T20:19:48Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-c8991e85190141a8a5526d7d743e134c2023-11-23T23:52:44ZengMDPI AGElectronics2079-92922022-10-011120328710.3390/electronics11203287IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture ModelYunyun Hou0Ruiyu He1Jie Dong2Yangrui Yang3Wei Ma4School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaSchool of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaThe Internet of Things (IoT) is increasingly providing industrial production objects to connect with the physical world and has been widely used in various fields. Although it has brought great industrial convenience, there are also potential security threats due to the vulnerabilities and malicious nodes in IoT. To correctly identify the traffic of malicious nodes in IoT and reduce the damage caused by malicious attacks on IoT devices, this paper proposes an autoencoder-based IoT malicious node detection method. The contributions of this paper are as follows: firstly, the high complexity multi-featured traffic data are processed and dimensionally reduced through the autoencoder to obtain the low-dimensional feature data. Then, the Bayesian Gaussian mixture model is adopted to cluster the data in a low-dimensional space to detect anomalies. Furthermore, the method of variational inference is used to estimate the parameters in the Bayesian Gaussian mixture model. To evaluate our model’s effectiveness, we used a public dataset for our experiments. As a result, in the experiment, the proposed method achieves a high accuracy rate of 99% distinguishing normal and abnormal traffic with three-dimension data reduced by the autoencoder, and it establishes our model’s better detection performance compared with previous K-means and Gaussian Mixture Model (GMM) solutions.https://www.mdpi.com/2079-9292/11/20/3287IoT securityanomaly detectionautoencoderBayesian Gaussian mixture model |
| spellingShingle | Yunyun Hou Ruiyu He Jie Dong Yangrui Yang Wei Ma IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model Electronics IoT security anomaly detection autoencoder Bayesian Gaussian mixture model |
| title | IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model |
| title_full | IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model |
| title_fullStr | IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model |
| title_full_unstemmed | IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model |
| title_short | IoT Anomaly Detection Based on Autoencoder and Bayesian Gaussian Mixture Model |
| title_sort | iot anomaly detection based on autoencoder and bayesian gaussian mixture model |
| topic | IoT security anomaly detection autoencoder Bayesian Gaussian mixture model |
| url | https://www.mdpi.com/2079-9292/11/20/3287 |
| work_keys_str_mv | AT yunyunhou iotanomalydetectionbasedonautoencoderandbayesiangaussianmixturemodel AT ruiyuhe iotanomalydetectionbasedonautoencoderandbayesiangaussianmixturemodel AT jiedong iotanomalydetectionbasedonautoencoderandbayesiangaussianmixturemodel AT yangruiyang iotanomalydetectionbasedonautoencoderandbayesiangaussianmixturemodel AT weima iotanomalydetectionbasedonautoencoderandbayesiangaussianmixturemodel |