mlsanityData to 14 Oct 2026

Privacy Enhancement for Gaze Data Using a Noise-Infused Autoencoder

arXiv 2508.10918 ↗First posted 1 Aug 2025cs.CV cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a privacy-enhancing mechanism for gaze signals using a latent-noise autoencoder that prevents users from being re-identified across play sessions without their consent, while retaining the usability of the data for benign tasks. We evaluate privacy-utility trade-offs across biometric identification and gaze prediction tasks, showing that our approach significantly reduces biometric identifiability with minimal utility degradation. Unlike prior methods in this direction, our framework retains physiologically plausible gaze patterns suitable for downstream use, which produces favorable privacy-utility trade-off. This work advances privacy in gaze-based systems by providing a usable and effective mechanism for protecting sensitive gaze data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 34 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

12 of 34 references.

References · 12

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
  3. 2017Semi-Adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Imagescited by 20
  4. 2020GazeBase: A Large-Scale, Multi-Stimulus, Longitudinal Eye Movement Datasetcited by 20
  5. 2021A privacy-preserving approach to streaming eye-tracking datacited by 13
  6. 2018Privacy-Aware Eye Tracking Using Differential Privacycited by 11
  7. 2019Differential Privacy for Eye-Tracking Datacited by 9
  8. 2022Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformationcited by 5
  9. 2024Privacy-Preserving Autoencoder for Collaborative Object Detectioncited by 5
  10. 2024Establishing a Baseline for Gaze-driven Authentication Performance in VR: A Breadth-First Investigation on a Very Large Datasetcited by 4
  11. 2024Privacy-Preserving Gaze Data Streaming in Immersive Interactive Virtual Reality: Robustness and User Experiencecited by 3
  12. 2023Adjustable Privacy using Autoencoder-based Learning Structurecited by 1

Built on by

Not cited yet.