A Method to Detect Machine Generated Domain Names Based on Random Forest Algorithm
Wenjie Song, Bin Li · 2016
In this paper, we proposed a method to detect machine generated domain names. Differences between the white list and the black list were analyzed to build a feature template from the angle of lexicology and linguistics. In contrast to the method based on the similarity, we adopted random forest algorithm to meet the demand of actual detection system by improving the generalization ability. Experimental results show that the method can not only achieve good performance in the efficiency and accuracy of detection, but also provide effective information support for security incidents.