# Discrete Few-Shot Learning for Pan Privacy

arXiv: https://arxiv.org/abs/2006.13120 · HTML: https://mlsanity.com/paper/2006.13120/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2020.

## Built on by (most cited first, 1 of 1)

- [Privacy Enhancement for Cloud-Based Few-Shot Learning](https://mlsanity.com/paper/2205.07864/) (2022)

## Abstract (arXiv)

In this paper we present the first baseline results for the task of few-shot learning of discrete embedding vectors for image recognition. Few-shot learning is a highly researched task, commonly leveraged by recognition systems that are resource constrained to train on a small number of images per class. Few-shot systems typically store a continuous embedding vector of each class, posing a risk to privacy where system breaches or insider threats are a concern. Using discrete embedding vectors, we devise a simple cryptographic protocol, which uses one-way hash functions in order to build recognition systems that do not store their users' embedding vectors directly, thus providing the guarantee of computational pan privacy in a practical and wide-spread setting.