Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Generating One-Hot Maps under Encryption

Ehud Aharoni, Nir Drucker, Eyal Kushnir, Ramy Masalha, Hayim Shaul

TL;DR

This work considers different tradeoffs that may affect the client's decision on how to pack and store one-hot maps and suggests several conversion algorithms when working with encrypted data.

Abstract

One-hot maps are commonly used in the AI domain. Unsurprisingly, they can also bring great benefits to ML-based algorithms such as decision trees that run under Homomorphic Encryption (HE), specifically CKKS. Prior studies in this domain used these maps but assumed that the client encrypts them. Here, we consider different tradeoffs that may affect the client's decision on how to pack and store these maps. We suggest several conversion algorithms when working with encrypted data and report their costs. Our goal is to equip the ML over HE designer with the data it needs for implementing encrypted one-hot maps.

Generating One-Hot Maps under Encryption

TL;DR

This work considers different tradeoffs that may affect the client's decision on how to pack and store one-hot maps and suggests several conversion algorithms when working with encrypted data.

Abstract

One-hot maps are commonly used in the AI domain. Unsurprisingly, they can also bring great benefits to ML-based algorithms such as decision trees that run under Homomorphic Encryption (HE), specifically CKKS. Prior studies in this domain used these maps but assumed that the client encrypts them. Here, we consider different tradeoffs that may affect the client's decision on how to pack and store these maps. We suggest several conversion algorithms when working with encrypted data and report their costs. Our goal is to equip the ML over HE designer with the data it needs for implementing encrypted one-hot maps.
Paper Structure (19 sections, 1 equation)

This paper contains 19 sections, 1 equation.

Table of Contents

  1. Introduction
  2. Branching.
  3. Our contribution.
  4. Organization.
  5. Preliminaries and notation
  6. Balanced binary trees
  7. HE
  8. HE Packing.
  9. Comparison under HE.
  10. Input representations
  11. One-hot map representation.
  12. Numeric representation.
  13. CRT representation.
  14. Hierarchical representation.
  15. Numeric (hierarchical) representation.
  16. ...and 4 more sections

Theorems & Definitions (1)

  • definition thmcounterdefinition