DGA Domain Name Detection Based on SVM Under Grey Wolf optimization Algorithm

At present, malwares are used by attackers to generate many malicious domain names and implant malicious instructions in malicious domain names. These bring huge losses to users that visit. This paper proposes a DGA domain name detection model based on SVM under GWO. It uses GWO to optimize the parameters of SVM and improve the search speed of optimal parameters. Through the training and testing for the domain name data set composed of the DGA domain names and the legal domain names, and the comparison of the traditional SVM algorithm classification, the results showed that the accuracy of the GWO optimized SVM classification algorithm reaches 97.49%, increased by 3.46%. With faster calculation speed and higher accuracy, the performance of the algorithm is significantly improved.