AndroClass: An Effective Method to Classify Android Applications by Applying Deep Neural Networks to Comprehensive Features

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2018/1250359/figures/1250359.fig.004a.svgz" name="1250359.fig.004a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Manifest-permission</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2018/1250359/figures/1250359.fig.004b.svgz" name="1250359.fig.004b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Manifest-complete</td></tr></table>

<div>Result of feature refinement for manifest information feature type with Google dataset.</div>

Wireless Communications and Mobile Computing

fig4

Figure 4

Figure 4: AndroClass: An Effective Method to Classify Android Applications by Applying Deep Neural Networks to Comprehensive Features 