Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features
The problems with network security that the Internet of Vehicles (IoV) faces are becoming more noticeable as it continues to evolve. Deep learning-based intrusion detection techniques can assist the IoV in preventing network threats. However, previous methods usually employ a single deep learning mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/9/4399 |
| _version_ | 1797601688870191104 |
|---|---|
| author | Ling Xing Kun Wang Honghai Wu Huahong Ma Xiaohui Zhang |
| author_facet | Ling Xing Kun Wang Honghai Wu Huahong Ma Xiaohui Zhang |
| author_sort | Ling Xing |
| collection | DOAJ |
| description | The problems with network security that the Internet of Vehicles (IoV) faces are becoming more noticeable as it continues to evolve. Deep learning-based intrusion detection techniques can assist the IoV in preventing network threats. However, previous methods usually employ a single deep learning model to extract temporal or spatial features, or extract spatial features first and then temporal features in a serial manner. These methods usually have the problem of insufficient extraction of spatio-temporal features of the IoV, which affects the performance of intrusion detection and leads to a high false-positive rate. To solve the above problems, this paper proposes an intrusion detection method for IoV based on parallel analysis of spatio-temporal features (PA-STF). First, we built an optimal subset of features based on feature correlations of IoV traffic. Then, we used the temporal convolutional network (TCN) and long short-term memory (LSTM) to extract spatio-temporal features in the IoV traffic in a parallel manner. Finally, we fused the spatio-temporal features extracted in parallel based on the self-attention mechanism and used a multilayer perceptron to detect attacks in the Internet of Vehicles. The experimental results show that the PA-STF method reduces the false-positive rate by 1.95% and 1.57% on the NSL-KDD and UNSW-NB15 datasets, respectively, with the accuracy and F1 score also being superior. |
| first_indexed | 2024-03-11T04:07:08Z |
| format | Article |
| id | doaj.art-b799c0017337400eabcd7bd54efd3d0d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:07:08Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b799c0017337400eabcd7bd54efd3d0d2023-11-17T23:43:52ZengMDPI AGSensors1424-82202023-04-01239439910.3390/s23094399Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal FeaturesLing Xing0Kun Wang1Honghai Wu2Huahong Ma3Xiaohui Zhang4School of Information Engineering, Henan University of Science and Technology, Luoyang 471000, ChinaSchool of Information Engineering, Henan University of Science and Technology, Luoyang 471000, ChinaSchool of Information Engineering, Henan University of Science and Technology, Luoyang 471000, ChinaSchool of Information Engineering, Henan University of Science and Technology, Luoyang 471000, ChinaSchool of Information Engineering, Henan University of Science and Technology, Luoyang 471000, ChinaThe problems with network security that the Internet of Vehicles (IoV) faces are becoming more noticeable as it continues to evolve. Deep learning-based intrusion detection techniques can assist the IoV in preventing network threats. However, previous methods usually employ a single deep learning model to extract temporal or spatial features, or extract spatial features first and then temporal features in a serial manner. These methods usually have the problem of insufficient extraction of spatio-temporal features of the IoV, which affects the performance of intrusion detection and leads to a high false-positive rate. To solve the above problems, this paper proposes an intrusion detection method for IoV based on parallel analysis of spatio-temporal features (PA-STF). First, we built an optimal subset of features based on feature correlations of IoV traffic. Then, we used the temporal convolutional network (TCN) and long short-term memory (LSTM) to extract spatio-temporal features in the IoV traffic in a parallel manner. Finally, we fused the spatio-temporal features extracted in parallel based on the self-attention mechanism and used a multilayer perceptron to detect attacks in the Internet of Vehicles. The experimental results show that the PA-STF method reduces the false-positive rate by 1.95% and 1.57% on the NSL-KDD and UNSW-NB15 datasets, respectively, with the accuracy and F1 score also being superior.https://www.mdpi.com/1424-8220/23/9/4399Internet of Vehiclesintrusion detectionspatio-temporal featuresnetwork security |
| spellingShingle | Ling Xing Kun Wang Honghai Wu Huahong Ma Xiaohui Zhang Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features Sensors Internet of Vehicles intrusion detection spatio-temporal features network security |
| title | Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features |
| title_full | Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features |
| title_fullStr | Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features |
| title_full_unstemmed | Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features |
| title_short | Intrusion Detection Method for Internet of Vehicles Based on Parallel Analysis of Spatio-Temporal Features |
| title_sort | intrusion detection method for internet of vehicles based on parallel analysis of spatio temporal features |
| topic | Internet of Vehicles intrusion detection spatio-temporal features network security |
| url | https://www.mdpi.com/1424-8220/23/9/4399 |
| work_keys_str_mv | AT lingxing intrusiondetectionmethodforinternetofvehiclesbasedonparallelanalysisofspatiotemporalfeatures AT kunwang intrusiondetectionmethodforinternetofvehiclesbasedonparallelanalysisofspatiotemporalfeatures AT honghaiwu intrusiondetectionmethodforinternetofvehiclesbasedonparallelanalysisofspatiotemporalfeatures AT huahongma intrusiondetectionmethodforinternetofvehiclesbasedonparallelanalysisofspatiotemporalfeatures AT xiaohuizhang intrusiondetectionmethodforinternetofvehiclesbasedonparallelanalysisofspatiotemporalfeatures |