English

Discrete Few-Shot Learning for Pan Privacy

Machine Learning 2020-06-24 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2006.13120,
  title  = {Discrete Few-Shot Learning for Pan Privacy},
  author = {Roei Gelbhart and Benjamin I. P. Rubinstein},
  journal= {arXiv preprint arXiv:2006.13120},
  year   = {2020}
}
R2 v1 2026-06-23T16:33:42.249Z