An Evaluation of One-Class and Two-Class Classification Algorithms for Keystroke Dynamics Authentication on Mobile Devices
Title | An Evaluation of One-Class and Two-Class Classification Algorithms for Keystroke Dynamics Authentication on Mobile Devices |
Publication Type | Conference Paper |
Year of Publication | 2015 |
Authors | Antal, M., Szabó, L. Z. |
Conference Name | 2015 20th International Conference on Control Systems and Computer Science |
Keywords | Android (operating system), Android devices, authentication, authentication test-framework, authorisation, biometrics, biometrics (access control), EER, equal error rate, Error analysis, feature extraction, Keyboards, keystroke dynamics, keystroke dynamics authentication, mobile authentication, mobile computing, mobile devices, Mobile handsets, one-class classification, one-class classification algorithms, pattern classification, pubcrawl170115, touch screen based devices, touch sensitive screens, touchscreen, Training, two-class classification algorithms |
Abstract | In this paper we study keystroke dynamics as an authentication mechanism for touch screen based devices. The authentication process decides whether the identity of a given person is accepted or rejected. This can be easily implemented by using a two-class classifier which operates with the help of positive samples (belonging to the authentic person) and negative ones. However, collecting negative samples is not always a viable option. In such cases a one-class classification algorithm can be used to characterize the target class and distinguish it from the outliers. We implemented an authentication test-framework that is capable of working with both one-class and two-class classification algorithms. The framework was evaluated on our dataset containing keystroke samples from 42 users, collected from touch screen-based Android devices. Experimental results yield an Equal Error Rate (EER) of 3% (two-class) and 7% (one-class) respectively. |
DOI | 10.1109/CSCS.2015.16 |
Citation Key | antal_evaluation_2015 |
- keystroke dynamics authentication
- two-class classification algorithms
- Training
- touchscreen
- touch sensitive screens
- touch screen based devices
- pubcrawl170115
- pattern classification
- one-class classification algorithms
- one-class classification
- Mobile handsets
- mobile devices
- mobile computing
- mobile authentication
- Android (operating system)
- keystroke dynamics
- Keyboards
- feature extraction
- Error analysis
- equal error rate
- EER
- biometrics (access control)
- biometrics
- authorisation
- authentication test-framework
- authentication
- Android devices