Privacy-Preserving Image Classification in the Local Setting

TL;DR

This paper introduces a privacy-preserving method for image classification that uses local differential privacy to perturb image representations, enabling secure machine learning without compromising sensitive visual information.

Contribution

It proposes a novel local perturbation technique and a supervised feature extractor, DCAConv, to balance privacy and utility in image classification tasks.

Findings

DCAConv maintains high data utility across multiple datasets.

The perturbation satisfies {}-LDP, ensuring privacy protection.

The method effectively balances privacy and classification accuracy.

Abstract

Image data has been greatly produced by individuals and commercial vendors in the daily life, and it has been used across various domains, like advertising, medical and traffic analysis. Recently, image data also appears to be greatly important in social utility, like emergency response. However, the privacy concern becomes the biggest obstacle that prevents further exploration of image data, due to that the image could reveal sensitive information, like the personal identity and locations. The recent developed Local Differential Privacy (LDP) brings us a promising solution, which allows the data owners to randomly perturb their input to provide the plausible deniability of the data before releasing. In this paper, we consider a two-party image classification problem, in which data owners hold the image and the untrustworthy data user would like to fit a machine learning model with these images as input. To protect the image privacy, we propose to locally perturb the image representation before revealing to the data user. Subsequently, we analyze how the perturbation satisfies {\epsilon}-LDP and affect the data utility regarding count-based and distance-based machine learning algorithm, and propose a supervised image feature extractor, DCAConv, which produces an image representation with scalable domain size. Our experiments show that DCAConv could maintain a high data utility while preserving the privacy regarding multiple image benchmark datasets.