Differential Privacy for Eye Tracking with Temporal Correlations

Abstract

New generation head-mounted displays, such as VR and AR glasses, are coming into the market with already integrated eye tracking and are expected to enable novel ways of human-computer interaction in numerous applications. However, since eye movement properties contain biometric information, privacy concerns have to be handled properly. Privacy-preservation techniques such as differential privacy mechanisms have recently been applied to eye movement data obtained from such displays. Standard differential privacy mechanisms; however, are vulnerable due to temporal correlations between the eye movement observations. In this work, we propose a novel transform-coding based differential privacy mechanism to further adapt it to the statistics of eye movement feature data and compare various low-complexity methods. We extend the Fourier perturbation algorithm, which is a differential privacy mechanism, and correct a scaling mistake in its proof. Furthermore, we illustrate significant reductions in sample correlations in addition to query sensitivities, which provide the best utility-privacy trade-off in the eye tracking literature. Our results provide significantly high privacy without any essential loss in classification accuracies while hiding personal identifiers.

In PLOS ONE

References in corpus (10)

• RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
• Pupil: An Open Source Platform for Pervasive Eye Tracking and Mobile Gaze-based Interaction
• Privacy-Aware Eye Tracking Using Differential Privacy
• Quantifying Differential Privacy in Continuous Data Release under Temporal Correlations
• A privacy-preserving approach to streaming eye-tracking data
• PrivacEye: Privacy-Preserving Head-Mounted Eye Tracking Using Egocentric Scene Image and Eye Movement Features
• Differential Privacy for Eye-Tracking Data
• Secure and Reliable Key Agreement with Physical Unclonable Functions
• Privacy Preserving Gaze Estimation using Synthetic Images via a Randomized Encoding Based Framework
• Privacy-Preserving Eye Videos using Rubber Sheet Model

Cited by in corpus (11)

• A privacy-preserving approach to streaming eye-tracking data
• Embedding Large Language Models into Extended Reality: Opportunities and Challenges for Inclusion, Engagement, and Privacy
• SoK: Data Privacy in Virtual Reality
• Privacy-preserving Scanpath Comparison for Pervasive Eye Tracking
• Privacy-Protecting Techniques for Behavioral Biometric Data: A Survey
• PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
• Eye Tracking Data Collection Protocol for VR for Remotely Located Subjects using Blockchain and Smart Contracts
• Correlated Data in Differential Privacy: Definition and Analysis
• 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
• Beyond the Headset: A Systematization of Knowledge on Extended Reality Privacy and Security in Healthcare
• Trade-offs in Privacy-Preserving Eye Tracking through Iris Obfuscation: A Benchmarking Study