[CHI’19] Adaptive VR by Implicit Behavioural Biometrics

We explored a mechanism to authenticate users in VR without effort in the user’s background. This can become quite important, considering the spread of head mounted devices in AR, VR, MR or XR, and the never-ending effort of having to authenticate to every session and use of a device. Of course, the headset itself could be an authenticator – like a smartphone – however, headsets could be shared with multiple people. It would be nice if the system knows this, and provides an adaptive UI, e.g., showing the right homescreen for each user.

The method analyses the user’s motion behaviour through controller and headset position and orientation, to identify users without entering a password or other explicit methods. The gathered eye, head, and hand information was analysed with machine learning to understand which patterns and features are unique to users, and thus suitable to identify them. This has been investigated across four common VR tasks, assessing data sampling and accuracy quality.

userid2 (1)

Top: vision of using body movement to authenticat users; bottom: different movements we studied

This work showed that 1) spatial relations between body parts are highly useful features, 2) user identification quality is dependent on the task conducted, 3) the dominant hand is a particularly useful to elicit unique user behaviour.

This work contributes another take on implicit sensing to improve the UI, but it also set me into the intersecting fields of usable security and biometrics. Its interdisciplinary nature, combining VR, Security, Motion Capture, and Machine learning, speaks to the interests of a wide audience. See more below:

Ken Pfeuffer, Matthias J. Geiger, Sarah Prange, Lukas Mecke, Daniel Buschek, and Florian Alt. 2019. Behavioural Biometrics in VR: Identifying People from Body Motion and Relations in Virtual Reality. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI ’19). Association for Computing Machinery, New York, NY, USA, Paper 110, 1–12. DOI:https://doi.org/10.1145/3290605.3300340

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s