Personal Identifiability of User Tracking Data During VR Training

Moore, Alec G.; McMahan, Ryan P.; Dong, Hailiang; Ruozzi, Nicholas

doi:10.1109/vrw52623.2021.00160

Cited by 7 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Miller et al (2020) identified users watching 360 °VR videos or answering VR questionnaires for several minutes. Following this work, Moore et al (2021) explored an e-learning scenario where VR users learned to troubleshoot medical robots in several stages. And recently, Rack et al (2022) compared different classification architectures using a dataset of participants talking to each other for longer periods.…”

Section: Specific Vs Non-specific Actionsmentioning

confidence: 99%

Who is Alyx? A new behavioral biometric dataset for user identification in XR

Rack,

Fernando,

Yalcin

et al. 2023

Front. Virtual Real.

View full text Add to dashboard Cite

Introduction: This paper addresses the need for reliable user identification in Extended Reality (XR), focusing on the scarcity of public datasets in this area.Methods: We present a new dataset collected from 71 users who played the game “Half-Life: Alyx” on an HTC Vive Pro for 45 min across two separate sessions. The dataset includes motion and eye-tracking data, along with physiological data from a subset of 31 users. Benchmark performance is established using two state-of-the-art deep learning architectures, Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU).Results: The best model achieved a mean accuracy of 95% for user identification within 2 min when trained on the first session and tested on the second.Discussion: The dataset is freely available and serves as a resource for future research in XR user identification, thereby addressing a significant gap in the field. Its release aims to facilitate advancements in user identification methods and promote reproducibility in XR research.

show abstract

Section: Specific Vs Non-specific Actionsmentioning

confidence: 99%

Who is Alyx? A new behavioral biometric dataset for user identification in XR

Rack,

Fernando,

Yalcin

et al. 2023

Front. Virtual Real.

View full text Add to dashboard Cite

show abstract

“…As well as uncovering potentially sensitive user information, XR data can also be used to personally identify users. For example, recent research has shown that a user can be personally identified though basic positional data within an VR experience to an accuracy of 90-95% [41,42].…”

Section: Related Work 21 Implications Of Xr Sensing For Users and Bys...mentioning

confidence: 99%

Implications of XR on Privacy, Security and Behaviour: Insights from Experts

Abraham

Saeghe

McGill

et al. 2022

Nordic Human-Computer Interaction Conference

View full text Add to dashboard Cite

Extended-Reality (XR) devices are packed with sensors that allow tracking of users (e.g., behaviour, actions, eye-gaze) and their surroundings (e.g., people, places, objects). As a consequence, XR devices pose significant risks to privacy, security, and our ability to understand and influence the behaviour of users -risks that will be amplified by ever-increasing adoption. This necessitates addressing these concerns before XR becomes ubiquitous. We conducted three focus groups with thirteen XR experts from industry and academia interested in XR, security, and privacy, to investigate current and emerging issues relating to security, privacy, and influencing behaviour. We identified issues such as virtual threats leading to physical harm, missing opting-out methods, and amplifying bias through perceptual filters. From the results we establish a collection of prescient challenges relating to security, privacy and behavioural manipulation within XR and present recommendations working towards developing future XR devices that better support security and privacy by default. CCS CONCEPTS• Human-centered computing → Mixed / augmented reality; • Security and privacy → Human and societal aspects of security and privacy.

show abstract

“…Prior work has demonstrated, based on basic captured positional tracking data, users can be uniquely identi ed with an accuracy of 95% [98], while soft biometric traits (e.g., body shape) can be obtained at a distance without an individual's cooperation [120]. Driven by advances in machine learning and computer vision, it will therefore be trivial for an AR device to segment, classify, and track individuals.…”

Section: Identity Anonymity and Biometric Idmentioning

confidence: 99%

“…While necessary, the requisite sensing capabilities of an AR device have the potential to open signi cant privacy and security risks for users and bystanders [10,52,124]. For instance, in addition to being able to uniquely identify their users [98], AR platforms will be able to gain insights into their users' mental/cognitive processes and phenomenological experiences [56,63], infer their stress/arousal levels and a ective states [3], and infer sensitive personal information and characteristics such as gender, age, ethnicity, and more [76]. This is possible due to the wealth of data captured by such devices from on-board cameras and microphones [92], as well as physiological and biometric sensing (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…As a result, bystanders may nd themselves deliberately or inadvertently subject to AR-enabled surveillance [116,145], with it being possible to sense and process biometric data (e.g. inferring identity from gait [98]), non-contact physiological data [136], volumetrically capture appearance and augment identity [77,123], determine protected characteristics [18], instrument behaviour and actions [101] and more [92]-predominantly from camera data alone. Research has shown that users may in fact be more concerned with risking bystanders' privacy, rather than their own; since bystanders could change their behaviour towards the AR user, if they perceive that their privacy is at risk [119].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Enhancing Technology and Everyday Augmented Reality

O’Hagan

Saeghe

Gugenheimer

et al. 2022

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

Fundamental to Augmented Reality (AR) headsets is their capacity to visually and aurally sense the world around them, necessary to drive the positional tracking that makes rendering 3D spatial content possible. This requisite sensing also opens the door for more advanced AR-driven activities, such as augmented perception, volumetric capture and biometric identification - activities with the potential to expose bystanders to significant privacy risks. Existing Privacy-Enhancing Technologies (PETs) often safeguard against these risks at a low level e.g., instituting camera access controls. However, we argue that such PETs are incompatible with the need for always-on sensing given AR headsets' intended everyday use. Through an online survey (N=102), we examine bystanders' awareness of, and concerns regarding, potentially privacy infringing AR activities; the extent to which bystanders' consent should be sought; and the level of granularity of information necessary to provide awareness of AR activities to bystanders. Our findings suggest that PETs should take into account the AR activity type, and relationship to bystanders, selectively facilitating awareness and consent. In this way, we can ensure bystanders feel their privacy is respected by everyday AR headsets, and avoid unnecessary rejection of these powerful devices by society.

show abstract

Personal Identifiability of User Tracking Data During VR Training

Cited by 7 publications

References 9 publications

Who is Alyx? A new behavioral biometric dataset for user identification in XR

Who is Alyx? A new behavioral biometric dataset for user identification in XR

Implications of XR on Privacy, Security and Behaviour: Insights from Experts

Privacy-Enhancing Technology and Everyday Augmented Reality

Contact Info

Product

Resources

About