Differential Privacy for Eye-Tracking Data

Abstract

As large eye-tracking datasets are created, data privacy is a pressing concern for the eye-tracking community. De-identifying data does not guarantee privacy because multiple datasets can be linked for inferences. A common belief is that aggregating individuals' data into composite representations such as heatmaps protects the individual. However, we analytically examine the privacy of (noise-free) heatmaps and show that they do not guarantee privacy. We further propose two noise mechanisms that guarantee privacy and analyze their privacy-utility tradeoff. Analysis reveals that our Gaussian noise mechanism is an elegant solution to preserve privacy for heatmaps. Our results have implications for interdisciplinary research to create differentially private mechanisms for eye tracking.

10 pages including appendix

References in corpus (2)

• Deep Learning with Differential Privacy
• Differential Privacy and Machine Learning: a Survey and Review

Cited by in corpus (13)

• A privacy-preserving approach to streaming eye-tracking data
• Differential Privacy for Eye Tracking with Temporal Correlations
• Going Incognito in the Metaverse: Achieving Theoretically Optimal Privacy-Usability Tradeoffs in VR
• The Security-Utility Trade-off for Iris Authentication and Eye Animation for Social Virtual Avatars
• SoK: Data Privacy in Virtual Reality
• Privacy Preserving Gaze Estimation using Synthetic Images via a Randomized Encoding Based Framework
• Privacy-Preserving Eye Videos using Rubber Sheet Model
• Privacy-Protecting Techniques for Behavioral Biometric Data: A Survey
• Privacy-preserving Scanpath Comparison for Pervasive Eye Tracking
• Adversarial Attacks on Classifiers for Eye-based User Modelling
• PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
• The Impact of Device Type, Data Practices, and Use Case Scenarios on Privacy Concerns about Eye-tracked Augmented Reality in the United States and Germany
• HydraGAN A Multi-head, Multi-objective Approach to Synthetic Data Generation