Privacy-Preserving Feature Coding for Machines

TL;DR

This paper introduces a privacy-preserving feature coding method for machine vision that reduces reconstructability of images while maintaining task accuracy, using adversarial training and autoencoders.

Contribution

A novel adversarial autoencoder-based approach that creates privacy-preserving latent representations for images, balancing privacy and task performance.

Findings

Input reconstruction reduced by 0.8 dB with minimal accuracy loss.

Achieves 30% bit savings over direct feature coding.

Privacy is enhanced by degradation near image edges.

Abstract

Automated machine vision pipelines do not need the exact visual content to perform their tasks. Therefore, there is a potential to remove private information from the data without significantly affecting the machine vision accuracy. We present a novel method to create a privacy-preserving latent representation of an image that could be used by a downstream machine vision model. This latent representation is constructed using adversarial training to prevent accurate reconstruction of the input while preserving the task accuracy. Specifically, we split a Deep Neural Network (DNN) model and insert an autoencoder whose purpose is to both reduce the dimensionality as well as remove information relevant to input reconstruction while minimizing the impact on task accuracy. Our results show that input reconstruction ability can be reduced by about 0.8 dB at the equivalent task accuracy, with degradation concentrated near the edges, which is important for privacy. At the same time, 30% bit savings are achieved compared to coding the features directly.