Automatic Whitelist-based Personal Digital Identity Protection Technology Research

With the development of the Internet, computer systems occupy a more and more important role in people's lives. Most of these computer systems require users'digital identities (e.g., username and password pairs) to authenticate the users so as to provide corresponding services. Therefore, it is very important to manage and protect these digital identities in the current computer systems, especially Web-based applications.In this paper, we propose a novel approach, referred to as Automated Individual White-List (AIWL), to manage and protect the users' digital identities. AIWL automatically maintains a white-list which contains the latest features of the login pages of user's all familiar web sites. Once a user tries to submit his/her digital identity to a web site that is not in the white-list or a web site whose features do not match the features in the white-list, AIWL will alert the user to possible attacks (phishing or pharming). Moreover, AIWL can efficiently defend against Pharming attack by checking the general features of a web site rather than the URL (Uniform Resource Locator) address only. So AIWL is securer than the existing tools that detect malicious web sites by URLs only. Furthermore, AIWL leverages a Naive Bayesian classifier to mine users'login processes so as to maintain the white-list automatically. Finally, we use experiments and user-oriented surveys to demonstrate that AIWL is an efficient, secure and practical tool for digital identities protection.