User Authentication Method Based On Fuzzy Clustering Analysis

In order to protect computer system, password is the most widely used method to control the access of computer system by authenticating the users' identity. However, the policy of password is vulnerable to impostor attacks due to its simplicity. Therefore, the original intention of keystroke dynamics is to provide a convenient and effective protection on password verification. In keystroke dynamics, the characteristics of users' keystroke are captured when password is being typed, and is analyzed by algorithms to automatically recognize the authentic identity. Up to now the known recognition algorithms mainly come from the field of statistics, neural networks, fuzzy logic, etc.Due to the weakness of traditional password systems on deterring password sharing and stolen, this dissertation describes a new method of fuzzy c-means clustering to enhance user authentication based on the keystroke authentication studied by researchers. Fuzzy C-Means is used to train the keystroke dynamics of users when entering passwords on a keyboard. After being trained, the system identifies whether a user is a legal user by comparing the current users' keystroke dynamics with his keystroke profile values within a certain precision threshold. The experiment results indicate that the proposed approach has a good discerning ability.