Privacy Enhancement for Cloud-Based Few-Shot Learning

TL;DR

This paper proposes a privacy-preserving embedding space for few-shot learning in untrusted environments, balancing privacy and accuracy through novel joint loss training and privacy methods.

Contribution

It introduces a new privacy-preserved representation learning method specifically designed for few-shot learning in cloud environments.

Findings

Privacy-preserved representations maintain model accuracy.

Different privacy methods impact the privacy-performance trade-off.

The proposed method effectively balances privacy and utility.

Abstract

Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains. However, deploying few-shot models in untrusted environments may inflict privacy concerns, e.g., attacks or adversaries that may breach the privacy of user-supplied data. This paper studies the privacy enhancement for the few-shot learning in an untrusted environment, e.g., the cloud, by establishing a novel privacy-preserved embedding space that preserves the privacy of data and maintains the accuracy of the model. We examine the impact of various image privacy methods such as blurring, pixelization, Gaussian noise, and differentially private pixelization (DP-Pix) on few-shot image classification and propose a method that learns privacy-preserved representation through the joint loss. The empirical results show how privacy-performance trade-off can be negotiated for privacy-enhanced few-shot learning.