LCHI: Low-Order Correlation and High-Order Interaction Integrated Model Oriented to Network Intrusion Detection

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/6830372/figures/6830372.fig.005a.svgz" name="6830372.fig.005a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Different MCA methods on the AWID dataset</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/6830372/figures/6830372.fig.005b.svgz" name="6830372.fig.005b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Different MCA methods on the NSL-KDD dataset</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/6830372/figures/6830372.fig.005c.svgz" name="6830372.fig.005c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Different MCA methods on the UNSW-NB15 dataset</td></tr><tr class="fig-image" id="d"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/6830372/figures/6830372.fig.005d.svgz" name="6830372.fig.005d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>Different MCA methods on the CICIDS 2018 dataset</td></tr></table>

<div>Detection results of different MCA methods. The number after the model bracket denotes the feature dimension (e.g., full MCA (2278d) means that there are 2278 dimension features generated by the full MCA method).</div>

Wireless Communications and Mobile Computing

fig5

Figure 5

Figure 5: LCHI: Low-Order Correlation and High-Order Interaction Integrated Model Oriented to Network Intrusion Detection 