Computer Based Behavioral Biometric Authentication via MultiModal Fusion

Biometric computer authentication has an advantage over password and access card authentication in that it is based on something you are, which is not easily copied or stolen. One way of performing biometric computer authentication is to use behavioral tendencies associated with how a user interacts with the computer. However, behavioral biometric authentication accuracy rates are much larger then more traditional authentication methods. This thesis presents a behavioral biometric system that fuses user data from keyboard, mouse, and Graphical User Interface (GUI) interactions. Combining the modalities results in a more accurate authentication decision based on a broader view of the user’s computer activity while requiring less user interaction to train the system than previous work. Testing over 30 users, shows that fusion techniques significantly improve behavioral biometric authentication accuracy over single modalities on their own. Two fusion techniques are presented, feature fusion and decision level fusion. Using an ensemble based classification method the decision level fusion technique improves the False Acceptance Rate (FAR) by 0.86 % and False Rejection Rate (FRR) by 2.98 % over the best individual modality. i