Skip to Main Content
User authentication based solely on user's password is the most commonly used method, but with several known issues. With the growing number of Internet users, most of whom are not familiar enough with security threats, as well as growing significance of their on-line activities, stolen passwords are becoming a major security problem. We argue that an additional, non-intrusive level of security can be achieved by analysing keystroke dynamics. A system was developed which uses an artificial neural network to discriminate between a genuine user and an impostor with a high success rate.