基于随机森林和深度神经网络的恶意域名检测方法

Detection of Malicious Domain Names Based on Random Forest and Deep Neural Network

针对使用域名生成算法(DGA)产生的恶意域名隐蔽性强,传统机器学习检测算法提取特征复杂以及检测效率低下等问题,提出了基于随机森林算法和深度学习组合的恶意域名检测方法。对恶意域名数据集使用随机森林的方法增强特征,利用深度学习方法进行检测分类,识别正常域名和恶意域名,并与传统方法进行对比,实验表明实验所用的方法检测效果要好。

The use of Domain Name Generation Algorithm(DGA)to generate malicious domain names has strong concealment,traditional machine learning detection algorithms have problems such as complex feature extraction and low detection efficiency,proposes a malicious domain name detection method based on the combination of random forest algorithm and deep learning.Use the random forest method to enhance the characteristics of the malicious domain name dataset,using deep learning methods for detection and classification,identifying normal and malicious domain names,The experiment shows that the detection effect of the method used is better.