A GRU-Based Lightweight System for CAN Intrusion Detection in Real Time

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Category</td><td class="align_center">Parameters</td></tr><tr><td class="align_left" colspan="2"><hr/></td></tr><tr><td class="align_left">CPU</td><td class="align_center">Nvidia Carmel ARM</td></tr><tr><td class="align_left">RAM</td><td class="align_center">8 GB unified memory</td></tr><tr><td class="align_left">GPU</td><td class="align_center">384-core Nvidia Volta GPU</td></tr><tr><td class="align_left">Operation system</td><td class="align_center">Ubuntu for Jetson</td></tr><tr><td class="align_left">CUDA version</td><td class="align_center">10.2</td></tr><tr><td class="align_left">Machine learning platform</td><td class="align_center">TensorFlow 2.4 + Scikit-learn 0.24</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Embedded device configuration for model inference.</div>

Security and Communication Networks

tab2

Table 2

Table 2: A GRU-Based Lightweight System for CAN Intrusion Detection in Real Time 