Villani Keystroke Dataset
Access to this repository is provided under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. In short, the dataset is intended for research and cannot be used for commercial applications.
Publications making use of this dataset should make the following citations:
- C. C. Tappert and S. Cha and M. Villani and R. S. Zack, "Keystroke Biometric Identification and Authentication on Long-Text Input", Int. Journal Information Security and Privacy (IJISP) 2010.
- Monaco, John V and Bakelman, Ned and Cha, Sung-Hyuk and Tappert, Charles C, "Developing a Keystroke Biometric System for Continual Authentication of Computer Users," European Intelligence and Security Informatics Conference (EISIC) 2012.
This dataset contains long free-text and fixed-text input from users answering essay questions and copying fables. Collected demographics include: platform, gender, age group, handedness, and awareness. The population conists of 144 university students and faculty that provided at least 5 samples each in different recording sessions. Samples contain an average of 746 keystrokes, with a mix of free-text and fixed-text input.
Users were instructed to respond to open ended essay questions. There are 1345 free-text samples
Users were instructed to copy a fable. There are 393 fixed-text samples. See the associated publications (especially 1) for more information.