Home     Books & Chapters     Publications     Video Lectures     Resources


Resources Related to Keystroke Dynamics and Person Identification


Short video on person identification based on keystroke dynamics



Video Lecture (conference talk)



Typing Pattern Data
(small, preprocessed dataset: 4 users, 200 typing sessions)

Here, you find the data we used for our experiments on person identification based on keystroke dynamics.

In both datasets, each line corresponds to a time series. In each line of the file, first, the user ID is given. This is followed by the time series. Please note that time series may have slightly different length due to typing errors made by the user. Also note that time series are ordered according to the time when they were donated by the users, i.e., the first time series is the one which was typed first.


Related Publications

D. Neubrandt, K. Buza (2017): Projection-based Person Identification, Proceedings of the 10th International Conference on Computer Recognition Systems (CORES), Springer. [ipynb] [Ipython Notebook in HTML]

K. Buza, Piroska B. Kis (2017): Towards Privacy-aware Keyboards, Proceedings of the 10th International Conference on Computer Recognition Systems (CORES), Springer. [video]

K. Buza (2016): Person Identification Based on Keystroke Dynamics: Demo and Open Challenge , 28th International Conference on Advanced Information Systems Engineering (CAiSE'16) Forum
See also: Person Identification Challenge

K. Buza, D. Neubrandt (2016): How You Type Is Who You Are, 11th International Symposium on Applied Computational Intelligence and Informatics, IEEE

K. Buza, D. Neubrandt (2016): A New Proposal for Person Identification Based on the Dynamics of Typing: Preliminary Results, Theoretical and Applied Informatics, Vol. 28, No. 1-2


Person Identification Challenge

We announced an open challenge on person identification based on keystroke dynamics. In association with the challenge, we published raw typing data containing more than 500 sessions.