Privatization of Synthetic Gaze: Attenuating State Signatures in Diffusion-Generated Eye Movements

TL;DR

This paper investigates how diffusion-based synthetic gaze data can effectively preserve essential signal features while attenuating privacy-sensitive internal state information, enhancing privacy in gaze-based applications.

Contribution

It demonstrates that diffusion-based gaze synthesis suppresses internal state signals while maintaining data quality, addressing privacy concerns in synthetic gaze data generation.

Findings

Synthetic gaze data shows trivial correlation with subjective internal states.

The approach preserves key signal characteristics similar to real gaze data.

Diffusion-based models effectively attenuate privacy-sensitive attributes.

Abstract

The recent success of deep learning (DL) has enabled the generation of high-quality synthetic gaze data. However, such data also raises privacy concerns because gaze sequences can encode subjects' internal states, like fatigue, emotional load, or stress. Ideally, synthetic gaze should preserve the signal quality of real recordings and remove or attenuate state-related, privacy-sensitive attributes. Many recent DL-based generative models focus on replicating real gaze trajectories and do not explicitly consider subjective reports or the privatization of internal states. However, in this work, we consider a recent diffusion-based gaze synthesis approach and examine correlations between synthetic gaze features and subjective reports (e.g., fatigue and related self-reported states). Our result shows that these correlations are trivial, which suggests the generative approach suppresses state-related features. Moreover, synthetic gaze preserves necessary signal characteristics similar to those of real data, which supports its use for privacy-preserving gaze-based applications.