Verifying identity via keystroke characteristics
International Journal of Man-Machine Studies
Verification of user identity via keyboard characteristics
Human factors in management information systems
Performance of the perceptron algorithm for the classification of computer users
SAC '92 Proceedings of the 1992 ACM/SIGAPP symposium on Applied computing: technological challenges of the 1990's
User identification via keystroke characteristics of typed names using neural networks
International Journal of Man-Machine Studies
A simulation evaluation study of neural network techniques to computer user identification
Information Sciences: an International Journal
Pattern recognition using neural networks: theory and algorithms for engineers and scientists
Pattern recognition using neural networks: theory and algorithms for engineers and scientists
Authentication via keystroke dynamics
Proceedings of the 4th ACM conference on Computer and communications security
Temporal sequence learning and data reduction for anomaly detection
ACM Transactions on Information and System Security (TISSEC)
Intrusion Detection: A Bioinformatics Approach
ACSAC '03 Proceedings of the 19th Annual Computer Security Applications Conference
User re-authentication via mouse movements
Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security
Correlation Pattern Recognition
Correlation Pattern Recognition
A New Biometric Technology Based on Mouse Dynamics
IEEE Transactions on Dependable and Secure Computing
Biometric authentication: a machine learning approach
Biometric authentication: a machine learning approach
| Hi-index | 0.00 |
In the internet age, security is a major concern as identity thefts often cause detrimental effects. Masquerading is an important factor for identity theft and current authentication systems using traditional methods woefully lack mechanisms to detect and prevent it. This paper presents an application independent, continual, non-intrusive, fast and easily deployable user re-authentication system based on behavioral biometrics. These behavioral attributes are extracted from the keyboard and mouse operations of the user. They are used to identify and nonintrusively authenticate the user periodically. To extract suitable user attributes, we propose a novel heuristic that uses the percentage of mouse-to-keyboard interaction ratio and interaction quotient (IQ). In the re-authentication process, every time, the current behavior of the user is compared with the stored "expected" behavior. All deviations are noted and after a certain deviation threshold is reached, the system logs the user out of the current session. The underlying heuristic prevents imposters from misusing the system. Experimental results show that the proposed heuristic can greatly improve the accuracy of application-based and application independent systems to 96.4% and 82.2% respectively.