Preventing Password Sharing: User Authentication via Fuzzy C-means Clustering Applied to Keystroke Profiles
نویسندگان
چکیده
This paper describes the design and implementation of an authentication system developed for preventing password sharing using fuzzy techniques applied to biometrical data. The c-Means clustering algorithm is implemented to create personal per-keyboard profiles based on the typing patterns of users. These profiles are accessed at logon time to further validate the identity of the user by comparing the fuzzy values obtained by a membership function applied to the input (i.e., keystroke intervals) with the values stored on the profile. If they match within a certain precision threshold defined by the administrator, then the user is granted access. Typing profiles are ciphered with the DES private-key cryptography algorithm using the actual passwords as keys and stored along with the ciphered passwords on the file system to provide a higher level of security.
منابع مشابه
Fuzzy and Markov Models for Keystroke Biometrics Authentication
Keystroke biometrics authentication system is based on a password and keystroke biometric features captured when a user is typing in the password. The system offers a higher level of security and convenience for computers. The system does not require additional hardware as it can be used with any existing keyboard, making it relatively inexpensive and fairly unobtrusive to the user. There have ...
متن کاملFuzzy aproach in biometric authentication by keystroke dynamics
A person’s identity verification became very important in information society. This article presents some results of our research of biometric authentication by keystroke dynamics. The comparison of the stochastic approach and using fuzzy numbers is presented as well. Key-Words: authentication, biometric, keystroke dynamics, password, fuzzy numbers
متن کاملDesign and Evaluation of a Pressure-Based Typing Biometric Authentication System
Although a variety of authentication devices to verify a user’s identity are in use today for computer access control, passwords have been and probably would remain the preferred method. Password authentication is an inexpensive and familiar paradigm that most operating systems support. However, this method is vulnerable to intruder access. This is largely due to the wrongful use of passwords b...
متن کاملMulti-Level User Authentication via Keystroke Dynamics
Behaviour biometric can provide a better alternative for traditional password methods and also for physiological biometrics due to the fact that they are very economical and easy to integrate with existing system. Various approaches have been made towards enhancing and improving the performance of keystroke dynamics system. The aim of writing this paper is to deal with all the possible uncertai...
متن کاملEnhanced Password Authentication Through Typing Biometrics With The K-Means Clustering Algorithm
Password authentication is the most commonly used identification system in today's computer world. It can be enhanced using typing biometrics as a secondary check. Our research focuses on using the time period between keystrokes as the measure of the typing pattern. Each user's typing pattern can be viewed as a cluster of measurements that can be differentiated from clusters of other users. The...
متن کامل