BiDA logo Biometrics and Data Pattern Analytics - BiDA Lab EPS logo UAM logo


  1. Download license agreement, send by email one signed and scanned copy to

  2. Send an email to, as follows:
    Subject: [DATABASE download: ATVS-Keystroke DB]

    : Your name, e-mail, telephone number, organization, postal mail, purpose for which you will use the database, time and date at which you sent the email with the signed license agreement.

  3. Once the email copy of the license agreement has been received at ATVS, you will get an email with a username, a password, and a time slot to download the database.

  4. Download the database, for which you will need to provide the authentication information given in step 4. After you finish the download, please notify by email to that you have successfully completed the transaction.

  5. For more information, please contact:


The ATVS-Keystroke database is a dataset captured for performance evaluation of Keystroke Dynamics recognition systems (see [IEEE16] for all the details). The database comprises 63 users with 12 genuine access and 12 impostor access for each user for a total number of samples equal to 7680 (63 users x 24 access x 5 data). There are people from two different nationalities with 60% of males and 40% females. The acquisition was made in two sessions according a semi-supervised protocol:

  • First session: the users were asked to introduce their personal data in the platform. This process was repeated 6 times.

  • Second dataset: after at least 24 hours, the user were asked to introduce once again their personal data in the platform. The process was repeated 6 times. In addition, in this second session, each user acted as an imposter trying to spoof the system with the personal data of other user. The personal data of other three users was showed to each of the imposter and they introduced them four times for a total number of impostor access of twelve per user.

The information provided by the users includes sensitive data and therefore, it has been post-processed to remove all the personal information (the characters pressed) and to maintain the privacy of the users enrolled in the database. The keystroke dynamic patterns were recorded using a key-logger (programmed in Java). The key-logger detects two different types of events: press and release. The timestamps for each of the detected event was recorded in milliseconds.


The dynamic features are stored in txt files with 5 sets of rows, separated by the feature name, that is:

  • HoldTime

  • RPLatency

  • PPLatency

  • RRLatency

  • PRLatency

For each feature, 5 different rows are included:

  • ROW 1: Keystroke features from Given Name.

  • ROW 2: Keystroke features from Family Name.

  • ROW 3: Keystroke features from Email.

  • ROW 4: Keystroke features from Nationality.

  • ROW 5: Keystroke features from ID Number.


The nomenclature followed in the datasets to name the files is as follows:

  • Genuine_XX_Y.txt

  • Impostor_XX_Y.txt

Where XX is the number of user (from 1 to 63) and Y the number of sample (from 1 to 12). The database includes the algorithms described in [IEEE16] and the file main.m can be used to reproduce all the experiments reported. All the algorithms are in Matlab code (tested on Matlab R2012a).


For further information on the database we refer the reader to (all these articles are publicly available in the publications section of the ATVS group webpage.)

  • [IEEE16] A. Morales, J. Fierrez, R. Tolosana, J. Ortega-Garcia, J. Galbally, M. Gomez-Barrero, A. Anjos and S. Marcel, "Keystroke Biometrics Ongoing Competition", IEEE Access, Vol. 4, pp. 7736-7746, November 2016.

  • [arxiv20] A. Acien, J.V. Monaco, A. Morales, R. Vera-Rodriguez, J. Fierrez, "TypeNet: Scaling up Keystroke Biometrics", arXiv:2004.03627, 2020.

Please remember to reference article [IEEE16] on any work made public, whatever the form, based directly or indirectly on any part of the ATVS-Keystroke DB.


  • The acquisition of this database has been supported by projects: COGNIMETRICS (TEC2015-70627-R MINECO/FEDER) and BEAT (FP7-SEC-284989 EU). The work of A. Morales was supported by JdC under Contract JCI-2012-12357 from Spanish MINECO.