Enhanced recognition of keystroke dynamics using Gaussian mixture models
Title | Enhanced recognition of keystroke dynamics using Gaussian mixture models |
Publication Type | Conference Paper |
Year of Publication | 2015 |
Authors | Çeker, H., Upadhyaya, S. |
Conference Name | MILCOM 2015 - 2015 IEEE Military Communications Conference |
Date Published | oct |
Keywords | authentication, biometrics, biometrics (access control), computer authentication, cryptographic protocols, digraph patterns, directed graphs, EER, enhanced recognition, equal error rate, error statistics, feature extraction, Gaussian density estimator, gaussian distribution, Gaussian mixture model, Gaussian Mixture Models, Gaussian processes, GMM, human computer interaction, image enhancement, image recognition, keystroke data, keystroke dynamics, learning (artificial intelligence), machine learning methods, mixture models, Outlier detection, pubcrawl170115, Standards |
Abstract | Keystroke dynamics is a form of behavioral biometrics that can be used for continuous authentication of computer users. Many classifiers have been proposed for the analysis of acquired user patterns and verification of users at computer terminals. The underlying machine learning methods that use Gaussian density estimator for outlier detection typically assume that the digraph patterns in keystroke data are generated from a single Gaussian distribution. In this paper, we relax this assumption by allowing digraphs to fit more than one distribution via the Gaussian Mixture Model (GMM). We have conducted an experiment with a public data set collected in a controlled environment. Out of 30 users with dynamic text, we obtain 0.08% Equal Error Rate (EER) with 2 components by using GMM, while pure Gaussian yields 1.3% EER for the same data set (an improvement of EER by 93.8%). Our results show that GMM can recognize keystroke dynamics more precisely and authenticate users with higher confidence level. |
DOI | 10.1109/MILCOM.2015.7357625 |
Citation Key | ceker_enhanced_2015 |
- Gaussian mixture model
- standards
- pubcrawl170115
- outlier detection
- mixture models
- machine learning methods
- learning (artificial intelligence)
- keystroke dynamics
- keystroke data
- image recognition
- image enhancement
- human computer interaction
- GMM
- Gaussian processes
- Gaussian Mixture Models
- authentication
- gaussian distribution
- Gaussian density estimator
- feature extraction
- error statistics
- equal error rate
- enhanced recognition
- EER
- directed graphs
- digraph patterns
- Cryptographic Protocols
- computer authentication
- biometrics (access control)
- biometrics