SSH Application Classification Based on Machine Learning
Machine Learning Theory and Practice · 2021
The security feature of SSH protocol ensures the privacy and security of communication content or communication behavior.Often, APTs and malware also use SSH or a variant encryption protocol disguised as SSH to invade a computer or server.In order to solve the shortcomings of existing SSH application classification research, this paper discusses the SSH protocol framework, SSH tunnel and C4.5 decision tree classification algorithm, and briefly discusses the data collection and system development tools of SSH application classification system in this paper.Moreover, the SSH classification model based on machine learning is designed and discussed.Finally, the proposed C4.5 decision tree classification algorithm is tested on the classification results of protocol application.Experimental data show that the average recall and accuracy of C4.5 decision tree classification algorithm for the five protocols are more than 93.17%.Therefore, the C4.5 decision tree classification algorithm proposed in this paper has certain advantages for SSH application classification.