A5070114175- Virtual Reality Applications and Impacts
- Gaze Tracking and Assistive Technology
- User Authentication and Security Systems
- Visual Attention and Saliency Detection
- Radiomics and Machine Learning in Medical Imaging
- Face Recognition and Perception
- Privacy, Security, and Data Protection
- Face recognition and analysis
- Retinal Imaging and Analysis
- Nuclear and radioactivity studies
- Biometric Identification and Security
- Opportunistic and Delay-Tolerant Networks
- Advanced Computing and Algorithms
- Visual perception and processing mechanisms
- Land Use and Ecosystem Services
- Personal Information Management and User Behavior
- Neural and Behavioral Psychology Studies
- Social Robot Interaction and HRI
- Augmented Reality Applications
- Privacy-Preserving Technologies in Data
- Ethics and Social Impacts of AI
- Urban Green Space and Health
- Impact of Light on Environment and Health
- Interactive and Immersive Displays
- IoT and Edge/Fog Computing
Virginia Tech
2023-2025
University of Florida
2021-2022
St. Brendan's Hospital
2022
Redmond Fire Department
2022
Meta (United States)
2021
With the increasing frequency of eye tracking in consumer products, including head-mounted augmented and virtual reality displays, gaze-based models have potential to predict user intent unlock intuitive new interaction schemes. In present work, we explored whether gaze dynamics can when a intends interact with real or digital world, which could be used develop predictive interfaces for low-effort input. Eye-tracking data were collected from 15 participants performing an item-selection task...
Eye-tracking technology is being increasingly integrated into mixed reality devices. Although critical applications are enabled, there significant possibilities for violating user privacy expectations. We show that an appreciable risk of unique identification even under natural viewing conditions in virtual reality. This would allow app to connect a user's personal ID with their work without needing consent, example. To mitigate such risks we propose framework incorporates gatekeeping via...
Virtual and mixed-reality (XR) technology has advanced significantly in the last few years will enable future of work, education, socialization, entertainment. Eye-tracking data is required for supporting novel modes interaction, animating virtual avatars, implementing rendering or streaming optimizations. While eye tracking enables many beneficial applications XR, it also introduces a risk to privacy by enabling re-identification users. We applied definitions it-anonymity plausible...
Augmented Reality (AR) devices are set apart from other mobile by the immersive experience they offer. While powerful suite of sensors on modern AR is necessary for enabling such an experience, can create unease in bystanders (i.e., those surrounding device during its use) due to potential bystander data leaks, which called privacy problem. In this paper, we propose BystandAR, first practical system that effectively protect visual (camera and depth) real-time with only on-device processing....
Mixed Reality (MR) devices are being increasingly adopted across a wide range of real-world applications, ranging from education and healthcare to remote work entertainment. However, the unique immersive features MR devices, such as 3D spatial interactions encapsulation virtual objects by invisible elements, introduce new vulnerabilities leading interaction obstruction misdirection. We implemented latency, click redirection, object occlusion, occlusion attacks within collaborative platform...
Eye-tracking is a critical source of information for understanding human behavior and developing future mixed-reality technology. enables applications that classify user activity or predict intent. However, eye-tracking datasets collected during common virtual reality tasks have also been shown to enable unique identification, which creates privacy risk. In this paper, we focus on the problem re-identification from features. We adapt standardized definitions k-anonymity plausible deniability...
Latest developments in computer hardware, sensor technologies, and artificial intelligence can make virtual reality (VR) spaces an important part of human everyday life. Eye tracking offers not only a hands-free way interaction but also the possibility deeper understanding visual attention cognitive processes VR. Despite these possibilities, eye-tracking data reveal privacy-sensitive attributes users when it is combined with information about presented stimulus. To address possibilities...
The use of ML models to predict a user's cognitive state from behavioral data has been studied for various applications which includes predicting the intent perform selections in VR. We developed novel technique that uses gaze-based adapt dwell-time thresholds aid gaze-only selection. A dataset users performing selection arithmetic tasks was used develop prediction (F1 = 0.94). GazeIntent dwell times based on model outputs and conducted an end-user study with returning new additional varied...
The modern mixed-reality devices that make the Metaverse viable require vast information about physical world and can also violate privacy of unsuspecting or unwilling bystanders. We provide an introduction to problem, existing solutions, avenues for future research.
Shoulder surfing attacks (SSAs) are a type of observation attack designed to illicitly gather sensitive data from "over the shoulder" victims. This can be directed at mobile devices, desktop screens, Personal Identification Number (PIN) pads an Automated Teller Machine (ATM), or written text. Existing solutions generally focused on authentication techniques (e.g., logins) and limited specific scenarios devices PIN Pads). We present ShotjldAR, usable system detect SSAs using multimodal eye...
Numerous studies have demonstrated that visuospatial attention is a requirement for successful working memory encoding. It unknown, however, whether this established relationship manifests in consistent gaze dynamics as people orient their toward an encoding target when searching information naturalistic environments. To test hypothesis, participants' eye movements were recorded while they searched and encoded objects virtual apartment (Experiment 1). We decomposed into 61 features capture...
Behavior-based authentication methods are actively being developed for XR. In particular, gaze-based promise continuous au-thentication of remote users. However, gaze behavior depends on the task performed. Identification rate is typically highest when comparing data from same task. this study, we compared performance using VR during random dot viewing, 360-degree image and a nuclear training simu-lation. We found that within-task performed best viewing (72%). The implication practitioners...
The modern Mixed Reality devices that make the Metaverse viable require vast information about physical world and can also violate privacy of unsuspecting or unwilling bystanders in their vicinity. In this article, we provide an introduction to problem, existing solutions, avenues for future research.
Video-based eye trackers capture the iris biometric and enable authentication to secure user identity. However, is susceptible spoofing another user's identity through physical or digital manipulation. The current standard identify attacks on eye-tracking sensors uses liveness detection. Liveness detection classifies gaze data as real fake, which sufficient detect presentation attacks. such defenses cannot a attack when image inputs are digitally manipulated swap pattern of person. We...
Video-based eye trackers capture the iris biometric and enable authentication to secure user identity. However, is susceptible spoofing another user's identity through physical or digital manipulation. The current standard identify attacks on eye-tracking sensors uses liveness detection. Liveness detection classifies gaze data as real fake, which sufficient detect presentation attacks. such defenses cannot a attack when image inputs are digitally manipulated swap pattern of person. We...
This paper presents our solution to the 2023 3DUI Contest challenge. Our goal was provide an immersive VR experience engage users in privately securing and accessing information Metaverse while improving authentication-related interactions inside virtual environment. To achieve this goal, we developed authentication method that uses a environment's individual assets as security tokens. improve token selection process, introduce HOG interaction technique. combines two classic techniques, Hook...
The use of ML models to predict a user's cognitive state from behavioral data has been studied for various applications which includes predicting the intent perform selections in VR. We developed novel technique that uses gaze-based adapt dwell-time thresholds aid gaze-only selection. A dataset users performing selection arithmetic tasks was used develop prediction (F1 = 0.94). GazeIntent dwell times based on model outputs and conducted an end-user study with returning new additional varied...
In the context of targeted advertisements and design, line between nudging manipulation is difficult to define, measure, enforce. The discussion what crosses users towards content they may find more enjoyable could manipulate them specific behaviors common when defining deceptive or dark patterns. Dark patterns are increasingly present in both web mobile contexts: producing interface designs that make it cancel subscriptions informed decisions differ from default settings. this position...
Augmented Reality (AR) devices are set apart from other mobile by the immersive experience they offer. While powerful suite of sensors on modern AR is necessary for enabling such an experience, can create unease in bystanders (i.e., those surrounding device during its use) due to potential bystander data leaks, which called privacy problem. In this poster, we propose BystandAR, first practical system that effectively protect visual (camera and depth) real-time with only on-device processing....