Abstract
Most of the existing systems require the users to provide a password or biometric data to authenticate themselves. However, as long as the user is still active in the system, there are no mechanisms to check whether the user is the genuine one or not. For the most computer system, the user identity is verified using Static Authentication (SA) only during the initial login process. In this paper, we focus on Continuous Authentication (CA) to continuously check the identity of the current user, based on every user action performed. We proposed to apply Artificial Immune System (AIS) Negative Selection (NS) for CA. Our proposed system was validated with a unique biometric dataset. The dataset was collected in a completely uncontrolled environment from 24 users. In this research, a combination of mouse and keystroke user behavior has been used.
Our proposed system, shows that AIS was correctly able to continuously authenticate the users with high accuracy. The best achieved accuracies for 10 NS runs, where the number of generated detectors is 100, 200, 300, and 600, are 97.74%, 99.01%, 99.275%, and 99.7% respectively.