A Low Computational Cost Method for Mobile Malware Detection Using Transfer Learning and Familial Classification Using Topic Modelling

<table class="table-group" id="tab7"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Data set</td><td class="align_center">Model</td><td class="align_center">Mean time to detect (MTTD) in seconds</td><td class="align_center">Computational power requirements</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Hybrid</td><td class="align_center">CNN</td><td class="align_center">90000</td><td class="align_center">Processor: Intel Xeon, GPU: Nvidia RTX 3080, RAM: 128 GB</td></tr><tr><td class="align_left" colspan="4"><hr/></td></tr><tr><td class="align_left">Malgenome</td><td class="align_center">Transfer learning</td><td class="align_center">61200</td><td class="align_center">Processor: Intel Core i9 10900K, GPU: Nvidia RTX 3060, RAM: 96 GB</td></tr><tr><td class="align_left" colspan="4"><hr/></td></tr><tr><td class="align_left">AAGM</td><td class="align_center">Transfer learning</td><td class="align_center">55944</td><td class="align_center">Processor: Intel Xeon, GPU: Nvidia RTX 3060, RAM: 96 GB</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of training time and computational power overhead.</div>

Applied Computational Intelligence and Soft Computing

tab7

Table 7

Table 7: A Low Computational Cost Method for Mobile Malware Detection Using Transfer Learning and Familial Classification Using Topic Modelling 