Identity verification using keystroke latencies | |
| Author | Tzou, Shiang-rong |
| Call Number | AIT Thesis no.CS-98-15 |
| Subject(s) | Computer security Computers--Access control--Keystroke timing authentication |
| Note | A thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Advanced Technologies |
| Publisher | Asian Institute of Technology |
| Abstract | Most of authorization mechanisms in computer security today are artificial. Generally, they require specific actions on the part of the user, many of which are not so friendly. Ideally, a typist should be able to approach a computer terminal, type his password, and be identified from keystroke characteristics. Individuals exhibit characteristic cognitive properties when interacting with the computer through a keyboard. In this research, by examining the properties of keying patterns and verifying its applied applicability, the traditional statistic recognition approaches are utilized first. A reference profile is built to serve as basis of comparison for future typing samples. The profile consists of the average time interval between keystrokes (mean keystroke latency) as well as a collection of the average times required to strike any two successive keys on the keyboard. Typing samples are scored against the reference profile and a score is calculated accessing the confidence that the same individual typed both the sample and the reference profile. There are two supervised(ADALINE, Backpropagation) and one unsupervised (Adaptive Resonance Theory) learning networks applied in classification procedures. In supervised learning, the training samples(authorized, impostor samples) are fed into the supervised network and the other testing sets are inputted into the trained net to evaluate the identification performance. In unsupervised learning, the ART can categorize the authorized samples into various clustered nodes according to the Euclidean similarity measurement between each sample. |
| Year | 1998 |
| Type | Thesis |
| School | School of Advanced Technologies (SAT) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Vatcharaporn Esichaikul; |
| Examination Committee(s) | Batanov, D. N. ;Sadananda R.; |
| Scholarship Donor(s) | Self - Support ; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 1998 |