Discrete Few-Shot Learning for Pan Privacy

• Published in: arXiv.org
• Main Authors: Gelbhart, Roei, Rubinstein, Benjamin I P
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 23.06.2020
• Subjects: Cryptography; Embedding; Learning; Object recognition; Privacy

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.