An Anomalous Traffic Detection Approach for the Private Network Based on Self-learning Model.

Although being isolated from the external network, the private network is still faced with some security threats, such as violations communications, malware attacks, and illegal operations. It is an attractive approach to recognize these security threats by discovering the underlying anomalous traffic. By studying the anomalous traffic detection technologies, an anomalous traffic detection approach is developed by capturing and analyzing the network packets, detecting the anomaly traffic that occurs in the network, and then detects anomalous behaviors of the network timely. In order to enhance its effectiveness and efficiency, a self-learning model is proposed and deployed in the detection approach. Finally, we conduct necessary evaluations about the proposed approach. The test results show that the approach can reach a good effect for detecting the unknown anomalous traffic.