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.006a.svgz" name="1250359.fig.006a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Google</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2018/1250359/figures/1250359.fig.006b.svgz" name="1250359.fig.006b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>APKPure</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2018/1250359/figures/1250359.fig.006c.svgz" name="1250359.fig.006c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Manual</td></tr></table>

<div>Accuracy comparison of different candidates for API calls feature type with all datasets.</div>

Wireless Communications and Mobile Computing

fig6

Figure 6

Figure 6: AndroClass: An Effective Method to Classify Android Applications by Applying Deep Neural Networks to Comprehensive Features 