Behavioural Biometrics in VR

Pfeuffer, Ken; Geiger, Matthias J.; Prange, Sarah; Mecke, Lukas; Buschek, Daniel; Alt, Florian

doi:10.1145/3290605.3300340

Cited by 131 publications

(53 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, Mustafa et al [28] recommend to use such functionality as an added layer of security in security-sensitive VR applications as pure behavioural biometrics might not be feasible in a large scale setting. This is inline with findings from Pfeuffer et al [29] who highlight the logarithmic decrease of accuracy with increasing group size, thus, making behavioural biometrics on its own not feasible for authentication in VR.…”

Section: Behavioural Biometric Authentication In Vrsupporting

confidence: 86%

“…Following a knowledge-driven behavioural biometric approach for user authentication in VR yielded promising results with classification accuracies up to 98.91% (N=23). This is noticeably higher than in previous works with a matching accuracy of 92.86% (N=14) [25] and 63.55% (N=22) [29]. This highlights the security benefits of applying DL on human behavioural biometrics collected during knowldge-driven authentication where a user enters their 4-digit PIN on RubikBiom (Figure 2).…”

Section: Lessons Learnt and Discussionmentioning

confidence: 68%

“…The Future of Authentication in VR Previous research transferred knowledge-based authentication schemes into VR [15,16,40] or leveraged head movements [2,28], hand movements [2,25,29], or gait signatures [31] for authentication in VR. In the case of behavioural biometric authentication [2,25,28,29,31], the direction is quite clear as researchers try to eliminate explicit authentication. This is mainly attributed to the fact that authentication is a secondary task users have to go through (e.g., unlocking a device) before being able to perform a main task (e.g., interacting in VR) [30].…”

Section: Lessons Learnt and Discussionmentioning

confidence: 99%

“…Based on findings and lessons learnt from previous works [12,15,17,25,28,29,39,40], we focus on the combination of a knowledge-based authentication scheme and corresponding human behavioural biometrics to increase security against observations. We apply DL on users' movement patterns during their knowledge-based authentication to make authentications more resistant to attacks (e.g., observation attacks, guessing attacks) in an unobtrusive way.…”

Section: Behavioural Biometric Authentication In Vrmentioning

confidence: 99%

“…Similar to previous work [29], we report top-1 classification accuracies (i.e., number of correct classifications divided by the total number). All our datasets are balanced as the number of authentications is the same for each class (user).…”

Section: Metricsmentioning

confidence: 99%

See 4 more Smart Citations

Knowledge-driven Biometric Authentication in Virtual Reality

Mathis

Fawaz

Khamis

2020

Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

With the increasing adoption of virtual reality (VR) in public spaces, protecting users from observation attacks is becoming essential to prevent attackers from accessing context-sensitive data or performing malicious payment transactions in VR. In this work, we propose RubikBiom, a knowledge-driven behavioural biometric authentication scheme for authentication in VR. We show that hand movement patterns performed during interactions with a knowledgebased authentication scheme (e.g., when entering a PIN) can be leveraged to establish an additional security layer. Based on a dataset gathered in a lab study with 23 participants, we show that knowledge-driven behavioural biometric authentication increases security in an unobtrusive way. We achieve an accuracy of up to 98.91% by applying a Fully Convolutional Network (FCN) on 32 authentications per subject. Our results pave the way for further investigations towards knowledge-driven behavioural biometric authentication in VR.

show abstract

Section: Behavioural Biometric Authentication In Vrsupporting

confidence: 86%

Section: Lessons Learnt and Discussionmentioning

confidence: 68%

Section: Lessons Learnt and Discussionmentioning

confidence: 99%

Section: Behavioural Biometric Authentication In Vrmentioning

confidence: 99%

Section: Metricsmentioning

confidence: 99%

See 3 more Smart Citations

Knowledge-driven Biometric Authentication in Virtual Reality

Mathis

Fawaz

Khamis

2020

Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

How to set safety boundary in virtual reality: A dynamic approach based on user motion prediction

Wang,

Che,

Chang

et al. 2023

Computer Animation & Virtual

View full text Add to dashboard Cite

Virtual reality (VR) interaction safety is a prerequisite for all user activities in the virtual environment. While seeking a deep sense of immersion with little concern about surrounding obstacles, users may have limited ability to perceive the real‐world space, resulting in possible collisions with real‐world objects. Nowadays, recent works and rendering techniques such as the Chaperone can provide safety boundaries to users but confines them in a small static space and lack of immediacy. To solve this problem, we propose a dynamic approach based on user motion prediction named SCARF, which uses Spearman's correlation analysis, rule learning, and few‐shot learning to achieve prediction of user movements in specific VR tasks. Specifically, we study the relationship between user characteristics, human motion, and categories of VR tasks and provides an approach that uses biomechanical analysis to define the interaction space in VR dynamically.We report on a user study with 58 volunteers and establish a three dimensional kinematic dataset from a VR game. The experiments validate that our few‐shot learning model is effective and can improve the performance of motion prediction. Finally, we implement SCARF in VR environment for dynamic safety boundary adjustment.

show abstract

Virtual Reality (VR) Safety Education for Ship Engine Training on Maintenance and Safety (ShipSEVR)

Markopoulos

Luimula

Porramo³

et al. 2020

Advances in Creativity, Innovation, Entrepreneurship and Communication of Design

View full text Add to dashboard Cite

The training and educational skills expected today from maritime engineers surpass their ability to follow them consistently. Such knowledge gap can impact significantly ship safety and operations. On this reality, ship engineers face multiple challenges related with the time required to be educated on each engine type, time needed to spend off the ship to acquire this training, the continuous training cost, and the easy access to complete engineering documentation and schematics. This paper attempts resolve these challenges with ShipSEVR (Ship Safety Education with Virtual Reality). The technology delivered has been achieved with the contribution of the smart technology company Wärtsilä and Ade with the contribution of VR development. TUAS, Ade, and Wärtsilä work close on research to optimize this engine room virtual reality training environment and impact ship and maritime safety. The paper demonstrates the industry challenge, technology architecture, working prototype, implementation methods, and adaptation techniques.

show abstract

Behavioural Biometrics in VR

Cited by 131 publications

References 35 publications

Knowledge-driven Biometric Authentication in Virtual Reality

Knowledge-driven Biometric Authentication in Virtual Reality

How to set safety boundary in virtual reality: A dynamic approach based on user motion prediction

Virtual Reality (VR) Safety Education for Ship Engine Training on Maintenance and Safety (ShipSEVR)

Contact Info

Product

Resources

About