Generating One-Hot Maps Under Encryption

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

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.
BibTeX
@inproceedings{aharoni2023generating,
  author = {Ehud Aharoni and Nir Drucker and Eyal Kushnir and Ramy Masalha and Hayim Shaul},
  title = {{Generating One-Hot Maps Under Encryption}},
  booktitle = {CSCML},
  year = {2023},
  doi = {10.1007/978-3-031-34671-2\_8},
}
Figure