PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval

TL;DR

This paper introduces PrivateMail, a novel differentially private supervised manifold learning method for image retrieval, demonstrating effective privacy-utility tradeoffs and practical efficiency.

Contribution

It presents the first differentially private supervised manifold learning technique and a private geometric embedding scheme for image retrieval.

Findings

Effective privacy-utility tradeoffs demonstrated

Method shows computational efficiency and practicality

First of its kind in differentially private supervised manifold learning

Abstract

Differential Privacy offers strong guarantees such as immutable privacy under post processing. Thus it is often looked to as a solution to learning on scattered and isolated data. This work focuses on supervised manifold learning, a paradigm that can generate fine-tuned manifolds for a target use case. Our contributions are two fold. 1) We present a novel differentially private method \textit{PrivateMail} for supervised manifold learning, the first of its kind to our knowledge. 2) We provide a novel private geometric embedding scheme for our experimental use case. We experiment on private "content based image retrieval" - embedding and querying the nearest neighbors of images in a private manner - and show extensive privacy-utility tradeoff results, as well as the computational efficiency and practicality of our methods.