Simulation of the Users' Email Behavior Based on BP-BDI Model

Abstract

With the development of the Internet, email has become a part of our life to communicate with each other. While bringing convenience for users, it also threats the users' network security. For example, if the user clicks on a malicious URL link in the email, the user's host is likely to be injected by virus, resulting in subsequent network security problems. We call the Internet users' operations on email "users' email behaviors". Through simulating the user's behavior on email, we can find the hidden dangers and threats of network security caused by user's operation on email. In this paper, BP-BDI model is proposed to simulate the user's behavior on email. The behavior learning module with BP neural network is constructed on the basis of BDI (Belief Desire Intention) model to learn the user's past behavior of email. As a result, the accuracy of simulating the user's email behavior will be improved. Finally, the experiment proves that the BP-BDI model can simulate the user's email behavior accurately and effectively.