About

Eakta Jain, Ph.D., is an associate professor in the Department of Computer & Information Science & Engineering at the University of Florida. She received her Ph.D. and M.S. degrees in Robotics from Carnegie Mellon University and her B.Tech. degree from IIT Kanpur. Her industry experience includes work at Texas Instruments R&D labs, Disney Research Pittsburgh, and the Walt Disney Animation Studios. Her research focuses on areas related to robotics, human-centered computing, and interactive technologies, contributing to the development of innovative solutions in these fields.

Research topics

• Computer Science
• Artificial Intelligence
• Computer Security
• Computer vision
• Data Mining
• Human–computer interaction
• Psychology
• Speech recognition
• Computer graphics (images)

Selected publications

• Toward Multimodal Privacy in XR: Design and Evaluation of Composite Privatization Methods for Gaze and Body Tracking Data

  IEEE Transactions on Visualization and Computer Graphics · 2026-03-30

  articleSenior author

  As extended reality (XR) systems become increasingly immersive and sensor-rich, they enable the collection of behavioral signals such as eye and body telemetry. These signals support personalized and responsive experiences and may also contain unique patterns that can be linked back to individuals. However, privacy mechanisms that naively pair unimodal mechanisms (e.g., independently apply privacy mechanisms for eye and body privatization) are often ineffective at preventing re-identification in practice. In this work, we systematically evaluate real-time privacy mechanisms for XR, both individually and in pair, across eye and body modalities. We assess privacy through re-identification rates and evaluate utility using numerical performance thresholds derived from existing literature to ensure real-time interaction requirements are met. We evaluated four eye and ten body mechanisms across multiple datasets, comprising up to 407 participants. Our results show that when carefully paired, multimodal mechanisms reduce re-identification rate from 80.3% to 26.3% in casual XR applications (e.g., VRChat and Job Simulator) and from 84.8% to 26.1 % in competitive XR applications (e.g., Beat Saber and Synth Riders), all while maintaining acceptable performance based on established thresholds. To facilitate adoption, we additionally release XR Privacy SDK, an open-source toolkit enabling developers to integrate the privacy mechanisms into XR applications for real-time use. These findings underscore the potential of modality-specific and context-aware privacy strategies for protecting behavioral data in XR environments.

  PublisherDOI

• Extending the Heilmeier Catechism to Evaluate Security and Privacy Systems: Who is Left Out?

  IEEE Security & Privacy · 2025-05-01

  article

  The Heilmeier Catechism consists of a set of questions that researchers and practitioners can consider when formulating research and applied engineering projects. In this article, we suggest explicitly asking who is included and who is left out of consideration.

  PublisherDOI

• Eye-Tracked Virtual Reality: A Comprehensive Survey on Methods and Privacy Challenges

  Proceedings of the IEEE · 2025-10-01 · 15 citations

  preprintOpen access

  The latest developments in computer hardware, sensor technologies, and artificial intelligence can make virtual reality (VR) and virtual spaces an important part of human everyday life. Eye tracking offers not only a hands-free way of interaction but also the possibility of a deeper understanding of human visual attention and cognitive processes in VR. Despite these possibilities, eye-tracking data also reveal users’ privacy-sensitive attributes when combined with the information about the presented stimulus. To address all, this survey first covers major works in eye tracking, VR, and privacy areas between 2012 and 2022. While eye tracking in VR part covers the computational eye-tracking pipeline from pupil detection and gaze estimation to offline data analysis, for privacy and security, we focus on eye-based authentication as well as computational methods to preserve the privacy of individuals and their eye-tracking data in VR. Later, we outline three main directions by focusing on privacy. In summary, this survey presents an extensive literature review of the utmost possibilities of eye tracking in VR and their privacy implications.

  PublisherDOI

• Toward Multimodal Privacy in XR: Design and Evaluation of Composite Privatization Methods for Gaze and Body Tracking Data

  arXiv (Cornell University) · 2025-06-16

  preprintOpen accessSenior author

  As extended reality (XR) systems become increasingly immersive and sensor-rich, they enable the collection of behavioral signals such as eye and body telemetry. These signals support personalized and responsive experiences and may also contain unique patterns that can be linked back to individuals. However, privacy mechanisms that naively pair unimodal mechanisms (e.g., independently apply privacy mechanisms for eye and body privatization) are often ineffective at preventing re-identification in practice. In this work, we systematically evaluate real-time privacy mechanisms for XR, both individually and in pair, across eye and body modalities. We assess privacy through re-identification rates and evaluate utility using numerical performance thresholds derived from existing literature to ensure real-time interaction requirements are met. We evaluated four eye and ten body mechanisms across multiple datasets, comprising up to 407 participants. Our results show that when carefully paired, multimodal mechanisms reduce re-identification rate from 80.3% to 26.3% in casual XR applications (e.g., VRChat and Job Simulator) and from 84.8% to 26.1% in competitive XR applications (e.g., Beat Saber and Synth Riders), all while maintaining acceptable performance based on established thresholds. To facilitate adoption, we additionally release XR Privacy SDK, an open-source toolkit enabling developers to integrate the privacy mechanisms into XR applications for real-time use. These findings underscore the potential of modality-specific and context-aware privacy strategies for protecting behavioral data in XR environments.

  PublisherOA PDFDOI

• Opto-diversity and Eye Tracking: Assumptions about ocular alignment in virtual reality eye tracking exclude users with strabismus and amblyopia

  ACM Transactions on Applied Perception · 2025-05-20

  articleSenior author

  Immersive, interactive virtual reality (VR) experiences rely on eye tracking data for a variety of applications. However, eye trackers assume that the user's eyes move in a coordinated way. We investigate how the violation of this assumption impacts the performance and subjective experience of users with strabismus and amblyopia. Our investigation follows a case study approach by analyzing in depth the qualitative and quantitative data collected during an interactive VR game by a small number of users with these visual impairments. Our findings reveal the ways in which assumptions about the default functioning of the eye can discourage or even exclude otherwise enthusiastic users from immersive VR. This study thus opens a new frontier for eye tracking research and practice.

  PublisherDOI

• Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms

  arXiv (Cornell University) · 2024-02-05

  preprintOpen accessSenior author

  Advances in face swapping have enabled the automatic generation of highly realistic faces. Yet face swaps are perceived differently than when looking at real faces, with key differences in viewer behavior surrounding the eyes. Face swapping algorithms generally place no emphasis on the eyes, relying on pixel or feature matching losses that consider the entire face to guide the training process. We further investigate viewer perception of face swaps, focusing our analysis on the presence of an uncanny valley effect. We additionally propose a novel loss equation for the training of face swapping models, leveraging a pretrained gaze estimation network to directly improve representation of the eyes. We confirm that viewed face swaps do elicit uncanny responses from viewers. Our proposed improvements significant reduce viewing angle errors between face swaps and their source material. Our method additionally reduces the prevalence of the eyes as a deciding factor when viewers perform deepfake detection tasks. Our findings have implications on face swapping for special effects, as digital avatars, as privacy mechanisms, and more; negative responses from users could limit effectiveness in said applications. Our gaze improvements are a first step towards alleviating negative viewer perceptions via a targeted approach.

  PublisherOA PDFDOI

• Dataset: Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience.

  Zenodo (CERN European Organization for Nuclear Research) · 2024-01-16

  datasetOpen accessSenior author

  DatasetThis repository contains the dataset from 'Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience'. The dataset features both raw and processed files from the two experiments described in the paper. File StructureThe root directory contains `raw` and `processed` folders. The `raw` folder features raw experiment files for each participant. Every participant is assigned a unique random ID and has corresponding event, headset, and validation files for the first experiment. Participants from the second experiment feature an additional survey file. The files in the `processed` folder report localized gaze angles useful for passing into eye tracking authentication/ re-identification models. `Example Videos` directory contains example videos. Exact data from the videos is not present in this dataset. The following represents the structure of the dataset (raw.zip and processed.zip) : .├── raw│ ├── E1 // experiment 1│ │ ├── cAaxbaeB // first participant│ │ │ ├── event_data.csv│ │ │ ├── headset_data.csv│ │ │ └── validation_data.csv│ │ ├── dzJnzpbc // second participant│ │ │ ├── event_data.csv│ │ │ ├── headset_data.csv│ │ │ └── validation_data.csv│ │ ├── ...│ │ └── zYCeDYZm // last participant│ │ ├── event_data.csv│ │ ├── headset_data.csv│ │ └── validation_data.csv│ └── E2 // experiment 2│ ├── AILlOGYd // first participant│ │ ├── event_data.csv│ │ ├── headset_data.csv│ │ ├── survey_data.csv│ │ └── validation_data.csv│ ├── AYfIOdjS // second participant│ │ ├── event_data.csv│ │ ├── headset_data.csv│ │ ├── survey_data.csv│ │ └── validation_data.csv│ ├── ...│ └── zDLzkWoS // last participant│ ├── event_data.csv│ ├── headset_data.csv│ ├── survey_data.csv│ └── validation_data.csv├── processed│ ├── E1 // experiment 1│ │ ├── cAaxbaeB.csv // first participant│ │ ├── dzJnzpbc.csv // second participant│ │ ...│ │ └── zYCeDYZm.csv // last participant│ └── E2 // experiment 2│ ├── AILlOGYd.csv // first participant│ ├── AYfIOdjS.csv // second participant│ ├── ...│ └── zDLzkWoS.csv // last participant License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. See LICENSE.md for more details. CitationWhen using the dataset, cite our work (to be updated upon publication): @article{wilson_privacy_2024, title={Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience}, author={Wilson, Ethan and Ibragimov, Azim and Proulx, Michael and Tetali, Sai Deep and Butler, Kevin and Jain, Eakta}, journal={IEEE Transactions on Visualization and Computer Graphics}, volume={}, number={}, year={2024}, pages={}, doi={}}

  PublisherDOI

• "I Had Sort of a Sense that I Was Always Being Watched...Since I Was": Examining Interpersonal Discomfort From Continuous Location-Sharing Applications

  2024-12-02 · 5 citations

  articleOpen access

  Continuous location sharing (CLS) applications are widely used for safety and social convenience. However, these applications have privacy concerns that can be used for control and harm. To understand user concerns, we performed the largest user study of CLS application usage performed to date, with 1500 of 3000 users indicating they use CLS applications and 896 of these users completing surveys. From survey responses, we conducted 23 interviews with participants who had uncomfortable experiences. With these interviews, we perform thematic analysis grounded by sociological frameworks of power dynamics and social exchange theory. We observe that CLS application users face discomfort related to three primary categories that build on each other: (1) overstepped boundaries, (2) continued discomfort, and (3) lifestyle-impacting behaviors. With this foundational understanding, we suggest features that aim to reduce relationship imbalances that CLS applications enable. Our resulting study demonstrates that CLS applications contribute to interpersonal discomfort, highlighting the need for design changes.

  PublisherOA PDFDOI

• Assistive Technology System for Highly Automated Vehicles to Support People with Mild Cognitive Impairment: A Human-Centered Design Approach

  AHFE international · 2024-01-01

  article

  Older adults with mild cognitive impairment (MCI) experience difficulties in memory, processing speed, attention, judgment, and visuospatial skills, which may impede the ability to perform various daily activities efficiently, including driving. The emergence of highly automated vehicles that do not require human intervention may offer significant benefits to individuals with MCI as these vehicles can increase mobility and independence. However, individuals with MCI may still be required to perform higher-level activities during a ride, which can be challenging for this user group. This research is focused on designing and prototyping a system that can help during trip planning and when interacting with an automated vehicle during normal and emergency operations. The proposed assistive technology system includes a secure mobile app, a real-time traveler monitoring system, an interactive in-vehicle agent for emergencies and safety functions, and a platform integrating all sub-systems with vehicle operations via a dashboard. The initial system requirements were identified through a series of interviews and focus groups with stakeholders, such as subject matter experts and older adults with and without MCI. Iterative participatory design sessions were further conducted to establish the information architecture and create visual and interactive designs. A final evaluation session with five individuals with MCI was conducted and showed favorable results in terms of system usability.

  PublisherDOI

• Dataset: Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience.

  Zenodo (CERN European Organization for Nuclear Research) · 2024-01-16

  datasetOpen accessSenior author

  DatasetThis repository contains the dataset from 'Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience'. The dataset features both raw and processed files from the two experiments described in the paper. File StructureThe root directory contains `raw` and `processed` folders. The `raw` folder features raw experiment files for each participant. Every participant is assigned a unique random ID and has corresponding event, headset, and validation files for the first experiment. Participants from the second experiment feature an additional survey file. The files in the `processed` folder report localized gaze angles useful for passing into eye tracking authentication/ re-identification models. `Example Videos` directory contains example videos. Exact data from the videos is not present in this dataset. The following represents the structure of the dataset (raw.zip and processed.zip) : .├── raw│ ├── E1 // experiment 1│ │ ├── cAaxbaeB // first participant│ │ │ ├── event_data.csv│ │ │ ├── headset_data.csv│ │ │ └── validation_data.csv│ │ ├── dzJnzpbc // second participant│ │ │ ├── event_data.csv│ │ │ ├── headset_data.csv│ │ │ └── validation_data.csv│ │ ├── ...│ │ └── zYCeDYZm // last participant│ │ ├── event_data.csv│ │ ├── headset_data.csv│ │ └── validation_data.csv│ └── E2 // experiment 2│ ├── AILlOGYd // first participant│ │ ├── event_data.csv│ │ ├── headset_data.csv│ │ ├── survey_data.csv│ │ └── validation_data.csv│ ├── AYfIOdjS // second participant│ │ ├── event_data.csv│ │ ├── headset_data.csv│ │ ├── survey_data.csv│ │ └── validation_data.csv│ ├── ...│ └── zDLzkWoS // last participant│ ├── event_data.csv│ ├── headset_data.csv│ ├── survey_data.csv│ └── validation_data.csv├── processed│ ├── E1 // experiment 1│ │ ├── cAaxbaeB.csv // first participant│ │ ├── dzJnzpbc.csv // second participant│ │ ...│ │ └── zYCeDYZm.csv // last participant│ └── E2 // experiment 2│ ├── AILlOGYd.csv // first participant│ ├── AYfIOdjS.csv // second participant│ ├── ...│ └── zDLzkWoS.csv // last participant License This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. See LICENSE.md for more details. CitationWhen using the dataset, cite our work (to be updated upon publication): @article{wilson_privacy_2024, title={Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experience}, author={Wilson, Ethan and Ibragimov, Azim and Proulx, Michael and Tetali, Sai Deep and Butler, Kevin and Jain, Eakta}, journal={IEEE Transactions on Visualization and Computer Graphics}, volume={}, number={}, year={2024}, pages={}, doi={}}

  PublisherDOI

Recent grants

• CRII: RI: Learning to Predict Temporal Interestingness for Videos

  NSF · $183k · 2016–2020

• Protecting the privacy of the child through facial identity removal in recorded behavioral observation sessions

  NIH · $416k · 2020–2024

• FW-HTF-P: Advancing the future work of nuclear operators through virtual reality-based training

  NSF · $182k · 2020–2023

Frequent coauthors

• Olivier Le Meur

  17 shared

• Kevin Butler

  14 shared

• Jessica K. Hodgins

  Carnegie Mellon University

  13 shared

• Yaser Sheikh

  12 shared

• Brendan David-John

  11 shared

• Ricardo Eiris

  Michigan Technological University

  10 shared

• Masoud Gheisari

  University of Florida

  10 shared

• Ethan Wilson

  University of Florida

  10 shared

Education

• Ph.D.

  University of Florida

Awards & honors

• Honorable Mention Best Paper: ACM Symposium on Applied Perce…
• Best Paper Award: Proceedings of the Symposium on Computer A…
• Google Anita Borg Finalist, 2008