User identification using GUI manipulation patterns and artificial neural networks

A masquerade attack is any attack in which the attacker is able to make the target system believe they are someone they are not. One particularly dangerous example of a masquerade attack occurs when an attacker uses an unattended, unlocked computer workstation. Recent studies have demonstrated that analyzing the manners in which a user manipulates a graphical user interface can be used as an effective means of authentication. We present the results of a study into the use of GUI manipulations in combination with Artificial Neural Networks (ANNs) as a basis for identification.