A Fusion Model Based on Dynamic Web Browsing Behavior Analysis for IoT Insider Threat Detection

With the wide application of Internet of things (IoT) devices in enterprises, the traditional boundary defense mechanisms are difficult to satisfy the demands of the insider threats detection. IoT insider threat detection can be more challenging, since internal employees are born with the ability to escape the deployed information security mechanism, such as firewalls and endpoint protection. In order to detect internal attacks more accurately, we can analyze users' web browsing behaviors to identify abnormal users. The existing web browsing behavior anomaly detection methods ignore the dynamic change of the web browsing behavior of the target user and the behavior consistency of the target user in its peer group, which results in a complex modeling process, low system efficiency and low detection accuracy. Therefore, the paper respectively proposes the individual user behavior model and the peer-group behavior model to characterize the abnormal dynamic change of user browsing behavior and compare the mutual behavioral inconsistency among one peer-group. Furthermore, the fusion model is presented for insider threat detection which simultaneously considers individual behavioral abnormal dynamic changes and mutual behavioral dynamic inconsistency from peers. The experimental results show that the proposed fusion model can accurately detect insider threat based on the abnormal user web browsing behaviors in the enterprise networks.