User Authentication Using One Class Learning Algorithm in Mouse Behavior

The quest for a reliable and convenient security mechanism to authenticate a computer user has existed since the inadequacy of conventional password mechanism was realized, first by the security community, and then gradually by the public. As data are moved from traditional localized computing environment to the new Cloud Computing paradigm, the need for better authentication has become more pressing. Recently, several large scale password leakages exposed users to an unprecedented risk of disclosure and abuse of their information. These incidents seriously shook public confidence in the security of the current information infrastructure; the inadequacy of password-based authentication mechanisms is becoming a major concern for the entire information society. Various potential solutions to this problem, a particularly promising technique is Mouse Dynamics. Mouse Dynamics measures and assesses auser's Mouse Behavior characteristics for use as a Biometric. Compared with other biometrics such as face, finger point and voice, Mouse Dynamics is less intrusive, and requires no specialized hardware to capture biometric information. Hence it is suitable for the current internet environment. When a user tries to log into a computer system, Mouse Dynamics only requires user to provide the login name and to perform a certain sequence of Mouse operations. Extracted behavioral feature's, based on mouse movements and clicks are compared to a legitimate user's profile. A match authenticates the user; otherwise user access is denied. Furthermore, a user's mouse behavior characteristics can be continually analyzed during user subsequent usage of a computer system for identity monitoring or intrusion detection.