A neural network based computer access security system for multiple users

A neural network architecture is proposed to deal with a situation of multiple users where each user has his/her own password with different length. Three experiments were conducted to find a better way for a computer access security system. The neural networks are trained using time intervals between successive keystrokes during password entry through keyboard. The performance of the neural networks designed for each of the experiments are evaluated in terms of recognition accuracy. Two major issues, preventive security and detection of violations, which may be in question for a security system, are examined. A procedure is proposed to make a security system more reliable when a time interval pattern close to the one produced by the group members during on-line entry.