An effective method for securing access to computers using a password is very important. Real time data was collected over a period of five weeks from six users by measuring time durations between keystrokes entered in a password. A phrase was used as the password. Extracting features from a set of measurements is a common practice in pattern recognition. Two methods are used. One of the methods used is based on dividing the set of measurements into three sets and then computing the mean value of each set (the three means). The other method is using the neighborhood averaging where each measurement is represented by itself and the other two neighbors. Even though the methods save memory, the classification results are not as good as hoped for. These methods do not lend themselves nicely to the problem at hand.

An approach to securing access to computer systems is described. By performing real-time measurements of the time durations between the keystrokes when a password is entered and using pattern-recognition algorithms, three online recognition systems were devised and tested. Two types of passwords were considered: phrases and individual names. A fixed phrase was used in the identification system. Individual names were used as a password in the verification system and in the overall recognition system. All three systems were tested and evaluated. The identification system used 10 volunteers and gave an indecision error of 1.2%. The verification system used 26 volunteers and gave an error of 8.1% in rejecting valid users and an error of 2.8% in accepting invalid users. The overall recognition system used 32 volunteers and gave an error of 3.1% in rejecting valid users and an error of 0.5% in accepting invalid users.>