SVM and GMM Based Unsupervised User-Behavior Evaluation Method for Heterogeneous Trustworthy Network

Trustworthy network is an inevitable trend in the development of high trusted computing and Internet. Behavior evaluation is an important research topic in trustworthy network. Till now, most effect focuses on the validity of host’s and user’s identity, such as integrity measurement and access control, which could not guarantee the trustworthiness of valid user’s behavior. In this paper, we proposed an unsupervised method for evaluating user’s network behavior and trustworthiness grades in a local heterogeneous network. First, we collected network behavior samples as more as possible. Then, they were tagged with different trustworthiness grades. According to the graded sample data, our method constructed a GMM model to evaluate user’s latter network behavior. And this model is again compared the performance under Support vector machine. The system can be deployed in a corporation indicated that our method could evaluate trustworthiness of users based on their network behaviors.