Privacy Preserving Gaze Estimation using Synthetic Images via a Randomized Encoding Based Framework

TL;DR

This paper introduces a privacy-preserving gaze estimation framework using synthetic images and randomized encoding, enabling real-time, accurate eye tracking without revealing sensitive personal information.

Contribution

It presents a novel randomized encoding framework for privacy-preserving eye gaze estimation using synthetic images, ensuring data privacy during model training and inference.

Findings

Works in real-time with accuracy comparable to non-private methods

Prevents data reconstruction of pupils, blinks, and scanpaths

Can be extended to other eye tracking applications

Abstract

Eye tracking is handled as one of the key technologies for applications that assess and evaluate human attention, behavior, and biometrics, especially using gaze, pupillary, and blink behaviors. One of the challenges with regard to the social acceptance of eye tracking technology is however the preserving of sensitive and personal information. To tackle this challenge, we employ a privacy-preserving framework based on randomized encoding to train a Support Vector Regression model using synthetic eye images privately to estimate the human gaze. During the computation, none of the parties learn about the data or the result that any other party has. Furthermore, the party that trains the model cannot reconstruct pupil, blinks or visual scanpath. The experimental results show that our privacy-preserving framework is capable of working in real-time, with the same accuracy as compared to non-private version and could be extended to other eye tracking related problems.