An Effective Insider Threat Detection Apporoach Based on BPNN.

With the increasing number of insider threat incidents, insider threat has become one of the most serious network security problems. Currently, the large volume of user data generated by various network systems and devices is difficult to analyze, and it is very difficult to detect abnormal user behavior among them. Meanwhile, existing insider threat detection methods cannot fully learn the important features of user data, resulting in a high false alarm rate and low accuracy. To solve these problems, we propose a novel insider threat method based on variational auto-encoder (VAE) and back propagation neural network (BPNN) in the paper. Initially, we use the generative model VAE to construct the normal user behavior model, and obtain the effective feature representation of user behavior. Then, we use the BPNN algorithm to detect abnormal user behavior from a large number of user activity logs. Finally, we conduct experiments to verify the detection performance of the proposed method. Experimental results indicate that the proposed detection method can achieve high accuracy and precision.