Personal identifiability of user tracking data during observation of 360-degree VR video

Virtual reality (VR) is a technology that is gaining traction in the consumer market. With it comes an unprecedented ability to track body motions. These body motions are diagnostic of personal identity, medical conditions, and mental states. Previous work has focused on the identifiability of body motions in idealized situations in which some action is chosen by the study designer. In contrast, our work tests the identifiability of users under typical VR viewing circumstances, with no specially designed identifying task. Out of a pool of 511 participants, the system identifies 95% of users correctly when trained on less than 5 min of tracking data per person. We argue these results show nonverbal data should be understood by the public and by researchers as personally identifying data.

[1]  Pamela J. Wisniewski,et al.  The Future of Networked Privacy: Challenges and Opportunities , 2015, CSCW Companion.

[2]  J. Tait,et al.  Challenges and opportunities. , 1996, Journal of psychiatric and mental health nursing.

[3]  Ioannis Tarnanas,et al.  Ecological Validity of Virtual Reality Daily Living Activities Screening for Early Dementia: Longitudinal Study , 2013, JMIR serious games.

[4]  Ashwin Ashok,et al.  Whose move is it anyway? Authenticating smart wearable devices using unique head movement patterns , 2016, 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[5]  Cha Zhang,et al.  Ensemble Machine Learning , 2012 .

[6]  Richard Matovu,et al.  Unsure How to Authenticate on Your VR Headset?: Come on, Use Your Head! , 2018, IWSPA@CODASPY.

[7]  B. Rothbaum,et al.  You can do that?!: Feasibility of virtual reality exposure therapy in the treatment of PTSD due to military sexual trauma. , 2019, Journal of anxiety disorders.

[8]  Wen Hu,et al.  GaitLock: Protect Virtual and Augmented Reality Headsets Using Gait , 2019, IEEE Transactions on Dependable and Secure Computing.

[9]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[10]  Sean Banerjee,et al.  Task-Driven Biometric Authentication of Users in Virtual Reality (VR) Environments , 2018, MMM.

[11]  Jeremy N. Bailenson,et al.  Automatically Detected Nonverbal Behavior Predicts Creativity in Collaborating Dyads , 2014 .

[12]  Florian Alt,et al.  Behavioural Biometrics in VR: Identifying People from Body Motion and Relations in Virtual Reality , 2019, CHI.

[13]  M. Bradley,et al.  Measuring emotion: the Self-Assessment Manikin and the Semantic Differential. , 1994, Journal of behavior therapy and experimental psychiatry.

[14]  Zuhair Bandar,et al.  FATHOM: A neural network-based non-verbal human comprehension detection system for learning environments , 2014, 2014 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[15]  Maja O’Connor.  LONGITUDINAL STUDY , 2013 .

[16]  Rosalind W. Picard,et al.  Automated Posture Analysis for Detecting Learner's Interest Level , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[17]  Taylor Beck,et al.  The ethical and privacy implications of mixed reality , 2019, SIGGRAPH 2019.

[18]  Krishna K. Venkatasubramanian,et al.  An approach for user identification for head-mounted displays , 2015, SEMWEB.

[19]  J. Bailenson,et al.  Social Attention in a Virtual Public Speaking Task in Higher Functioning Children With Autism , 2013, Autism research : official journal of the International Society for Autism Research.

[20]  Jeremy Bailenson,et al.  Protecting Nonverbal Data Tracked in Virtual Reality , 2018, JAMA pediatrics.

[21]  Evelyne Klinger,et al.  Use of the Virtual Action Planning Supermarket for the Diagnosis of Mild Cognitive Impairment , 2009, Dementia and Geriatric Cognitive Disorders.

[22]  Rakesh M. Verma,et al.  International Workshop on Security And Privacy Analytics , 2016, IWSEC 2016.

[23]  Albert A. Rizzo,et al.  Diagnosing Attention Disorders in a Virtual Classroom , 2004, Computer.

[24]  Jeremy N. Bailenson,et al.  Automatic Detection of Nonverbal Behavior Predicts Learning in Dyadic Interactions , 2014, IEEE Transactions on Affective Computing.

[25]  J. Bailenson,et al.  Stimulus Sampling With 360-Videos: Examining Head Movements, Arousal, Presence, Simulator Sickness, and Preference on a Large Sample of Participants and Videos , 2020, IEEE Transactions on Affective Computing.

[26]  Diane Hosfelt,et al.  Making ethical decisions for the immersive web , 2019, ArXiv.

[27]  E. Cherniack.  Not just fun and games: applications of virtual reality in the identification and rehabilitation of cognitive disorders of the elderly , 2011, Disability and rehabilitation. Assistive technology.