Datasets

To obtain access to any of the following datasets, send me an email with the following information:

1. Your name and institution
2. The dataset(s) you would like access to

You will then be added to the repository. I approve all requests, I just like to keep track of how the data is used and track/fix any issues that might arise with the data. Access is provided under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. In short, the datasets are intended for research and cannot be used for commercial applications. More information is located on each dataset wiki page.

• Perez keystroke
  Users typing with one hand and both hands to simulate an obstruction. See also the OhKBIC data.

• Four HCI tasks
  Mouse and keystroke data from users performing four common computing tasks.

• Villani keystroke
  Keystroke data from users answering open-ended questions and copying fixed text.

• Stewart keystroke
  Keystroke and stylometry data from students taking online exams.

• Bakelman keypad
  Keypad (on a desktop keyboard) data entry of a telephone number.

• Coakley mobile
  Soft keyboard and gesture input on Android mobile devices.

• Moodle quizzes
  Mouse pointer motion collected during multiple choice quizzes.

• Nursery rhymes
  Keystroke data from users copying several nursery rhymes.

Other public datasets

---

These datasets I do not maintain. Please see instructions on the external link to obtain access or contact the authors.

Keystroke

• CMU Keystroke Dynamics – Benchmark Data Set
  51 users typing the password (.tie5Roanl)

• CMU Free vs. Transcribed Text
  20 users free and transcribed text

• Keystroke Dynamics – Android platform
  42 users typing the password (.tie5Roanl) on a mobile device

• BeiHang Keystroke Dynamics Database
  209 users typing various passwords

• BioChaves Keystroke Databases
  47 users typing four words

• Keystroke100 Dataset
  100 users typing a password (try4-mbs) on a pressure-sensitive keyboard

• GREYC Keystroke Datasets
  There are 3 different datasets available:
  133 users typing various passwords
  118 users typing various passwords and usernames
  110 users typing five passphrases

• RHU KeyStroke Dynamics Benchmark Dataset
  51 users typing the password (rhu.university) on a mobile device

• CITEFA Keystroke Dynamics Dataset (broken link)
  63 users typing copying literature text

• ATVS-Keystroke DB (available upon request)
  63 users typing their personal information

• LSIA Keystroke Dynamics keypress latency dataset
  Physicians typing patient summaries over 1 week

• Stonybrook Keystroke Patterns as Prosody in Digital Writings
  196 users typing free text

• Keystroke acoustics, video, and timings (available upon request)
  81 users typing fixed and free text

• Detecting Age Groups using Keystroke Dynamics
  100 users typing fixed text

• How We Type
  30 users typing various inputs with motion capture, eye tracking, and video

• MOBIKEY Keystroke Dynamics Password Database
  54 users typing easy and strong passwords on a mobile device

• Statistical Analysis of Personality and Identity in Chats (available upon request)
  50 users chatting with an unknown operator

Mouse click and motion

• Shen mouse behavior for static authentication
  56 users performing fixed operations

• Shen mouse behavior for continuous authentication
  28 users performing routine activities

• University of Victoria mouse dynamics
  48 users in realistic environment over several months

• Balabit Mouse Challenge Dataset
  10 users motion and click behavior