Privacy Enhancement for Cloud-Based Few-Shot Learning
This addresses privacy concerns for users deploying few-shot learning models in untrusted environments like the cloud, though it is incremental in combining existing privacy techniques with few-shot learning.
The paper tackles the problem of privacy risks in cloud-based few-shot learning by proposing a novel privacy-preserved embedding space, showing that methods like differentially private pixelization can negotiate a trade-off between privacy and model accuracy.
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.