A Deep Learning-Based Intrusion Detection Model Integrating Convolutional Neural Network and Vision Transformer for Network Traffic Attack in the Internet of Things

被引:0
作者
Du, Chunlai [1 ]
Guo, Yanhui [2 ]
Zhang, Yuhang [1 ]
机构
[1] North China Univ Technol, Sch Informat Sci & Technol, Beijing 100144, Peoples R China
[2] Univ Illinois, Dept Comp Sci, Springfield, IL 62703 USA
基金
中国国家自然科学基金;
关键词
intrusion detection; Internet of Things; deep learning; transformer; IOT; DATASET;
D O I
10.3390/electronics13142685
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the rapid expansion and ubiquitous presence of the Internet of Things (IoT), the proliferation of IoT devices has reached unprecedented levels, heightening concerns about IoT security. Intrusion detection based on deep learning has become a crucial approach for safeguarding IoT ecosystems. However, challenges remain in IoT intrusion detection research, including inadequate feature representation at the classifier level and poor correlation among extracted traffic features, leading to diminished classification accuracy. To address these issues, we propose a novel transformer-based IoT intrusion detection model, MBConv-ViT (MobileNet Convolution and Vision Transformer), which enhances the correlation of extracted features by fusing local and global features. By leveraging the high correlation of traffic flow, our model can identify subtle differences in IoT traffic flow, thereby achieving precise classification of attack traffic. Experiments based on the open datasets TON-IoT and Bot-IoT demonstrate that the accuracy of the MBConv-ViT model, respectively, 97.14% and 99.99%, is more effective than several existing typical models.
引用
收藏
页数:15
相关论文
共 30 条
  • [1] TON_IoT Telemetry Dataset: A New Generation Dataset of IoT and IIoT for Data-Driven Intrusion Detection Systems
    Alsaedi, Abdullah
    Moustafa, Nour
    Tari, Zahir
    Mahmood, Abdun
    Anwar, Adnan
    [J]. IEEE ACCESS, 2020, 8 : 165130 - 165150
  • [2] [Anonymous], 2019, The Growth in Connected IoT Devices Is Expected to Generate 79.4ZB of Data in 2025
  • [3] Anomaly Based Intrusion Detection System Using Hierarchical Classification and Clustering Techniques
    Bahjat, Hala
    Mohammed, Suhaila N.
    Ahmed, Wafaa
    Hamad, Sumaya
    Mohammed, Shayma
    [J]. 2020 13TH INTERNATIONAL CONFERENCE ON DEVELOPMENTS IN ESYSTEMS ENGINEERING (DESE 2020), 2020, : 257 - 262
  • [4] PDAE: Efficient network intrusion detection in IoT using parallel deep auto-encoders
    Basati, Amir
    Faghih, Mohammad Mehdi
    [J]. INFORMATION SCIENCES, 2022, 598 : 57 - 74
  • [5] Cetin B, 2019, IEEE INT CONF BIG DA, P6004, DOI [10.1109/BigData47090.2019.9005507, 10.1109/bigdata47090.2019.9005507]
  • [6] Chhabra Mohit, 2022, Mobile Radio Communications and 5G Networks: Proceedings of Second MRCN 2021. Lecture Notes in Networks and Systems (339), P297, DOI 10.1007/978-981-16-7018-3_23
  • [7] Xception: Deep Learning with Depthwise Separable Convolutions
    Chollet, Francois
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1800 - 1807
  • [8] Network intrusion detection based on BiSRU and CNN
    Ding, Shanshuo
    Wang, Yingxin
    Kou, Liang
    [J]. 2021 IEEE 18TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SMART SYSTEMS (MASS 2021), 2021, : 145 - 147
  • [9] IoT Intrusion Detection System Using Deep Learning and Enhanced Transient Search Optimization
    Fatani, Abdulaziz
    Abd Elaziz, Mohamed
    Dahou, Abdelghani
    Al-Qaness, Mohammed A. A.
    Lu, Songfeng
    [J]. IEEE ACCESS, 2021, 9 : 123448 - 123464
  • [10] Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study
    Ferrag, Mohamed Amine
    Maglaras, Leandros
    Moschoyiannis, Sotiris
    Janicke, Helge
    [J]. JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2020, 50