Evaluation of Deep Learning Methods Efficiency for Malicious and Benign System Calls Classification on the AWSCTD

<div>Confusion matrix of the GRU and CNN methods for the 100 system calls sequence of the AllMalwarePlusClean data sample. Class labels: AdWare (a); Benign (b); DangerousObject (c); Downloader (d); Trojan (e); WebToolbar (f).</div>

Security and Communication Networks

fig5

Figure 5

Figure 5: Evaluation of Deep Learning Methods Efficiency for Malicious and Benign System Calls Classification on the AWSCTD 