Abstract
This study explores the potential privacy risks associated with the use of behavioural data as an identification mechanism in immersive VR applications. With the advent of modern VR technology, tracking sensors are now able to provide a highly immersive experience with a high level of user agency, significantly increasing both the amount and richness of behavioural data being collected and recorded. However, there has been little research into the privacy risks of such approaches. In this work, we investigate the capability of machine learning algorithms to identify VR users across multiple sessions and activities, as well as their effectiveness when users deliberately change their behaviour to evade detection. We also examine how the physical characteristics of users impact the accuracy of these algorithms. Our results show that once a user is tracked in VR, they can be identified with 83% accuracy across multiple sessions of the same activity and with 80% accuracy when performing a different task. Even when users attempt to deliberately obfuscate their behaviour, they can still be recognised with 78% accuracy. These findings highlight the need for more robust technical measures to safeguard the behavioural privacy of VR users.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.