DGA and DNS Covert Channel Detection System based on Machine Learning

In recent years, the application of covert channel to ensure network security has attracted more and more attention from scholars and network attackers, but the research on its detection is relatively few. We propose a DGA and DNS covert channel detection system based machine learning, using improved TF-IDF, specificity score and other algorithms to detect malicious domain names. The experimental results show that the accuracy of the system in detecting malicious domain names is 99.92%.