Abstract
Network intrusion poses a severe threat to the Internet of Things (IoT). Thus, it is essential to study information security protection technology in IoT. Learning sophisticated feature interactions is critical in improving detection accuracy for network intrusion. Despite significant progress, existing methods seem to have a strong bias towards single low‐ or high‐order feature interaction. Moreover, they always extract all possible low‐order interactions indiscriminately, introducing too much noise. To address the above problems, we propose a low‐order correlation and high‐order interaction (LCHI) integrated feature extraction model. First, we selectively extract the beneficial low‐order correlation between the same‐type features by the multivariate correlation analysis (MCA) model and attention mechanism. Second, we extract the complicated high‐order feature interaction by the deep neural network (DNN) model. Finally, we emphasize both the low‐ and high‐order feature interactions and incorporate them. Our LCHI model seamlessly combines the linearity of MCA in modeling lower‐order feature correlation and the nonlinearity of DNN in modeling higher‐order feature interaction. Conceptually, our LCHI is more expressive than the previous models. We carry on a series of experiments on the public wireless and wired network intrusion detection datasets. The experimental results show that LCHI improves 1.06%, 2.46%, 3.74%, 0.25%, 1.17%, and 0.64% on the AWID, NSL‐KDD, UNSW‐NB15, CICIDS 2017, CICIDS 2018, and DAPT 2020 datasets, respectively.
Highlights
The COVID-19 pandemic in 2020 moved the main scenes of people’s lives and work from offline to the Internet overnight
Following contributions have been made in this paper: (1) To extract features more perfectly, we integrate the low-order correlation captured by the multivariate correlation analysis (MCA) model and the high-order interaction obtained by the deep neural network (DNN) model
(4) To evaluate the effectiveness and robustness of our low-order correlation and high-order interaction (LCHI) model, we conduct a series of experiments on public wireless (e.g., Aegean WiFi intrusion dataset (AWID)) and wire datasets (e.g., NSL-KDD, UNSW-NB15, CICIDS 2017, CICIDS 2018, and DAPT 2020)
Summary
The COVID-19 pandemic in 2020 moved the main scenes of people’s lives and work from offline to the Internet overnight. (1) To extract features more perfectly, we integrate the low-order correlation captured by the MCA model and the high-order interaction obtained by the DNN model (2) To characterize low-order correlation more effectively, we comprehensively analyze the difference of features and divide them into different types. We selectively extract the useful low-order correlation between features in the same type, avoiding the dimension disaster and too much noise or correlation loss (3) To consider the classification influence in generated correlations, we employ attention to estimate the importance of different correlations when incorporating their latent representations (4) To evaluate the effectiveness and robustness of our LCHI model, we conduct a series of experiments on public wireless (e.g., AWID) and wire datasets (e.g., NSL-KDD, UNSW-NB15, CICIDS 2017, CICIDS 2018, and DAPT 2020).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
