SecTL: Secure and Verifiable Transfer Learning-based inference

Abbass Madi, Oana Stan, Renaud Sirdey, Cédric Gouy-Pailler

2022

Abstract

This paper investigates the possibility of realizing complex machine learning tasks over encrypted inputs with guaranteed integrity. Our approach combines Fully Homomorphic Encryption (FHE) and Verifiable Computing (VC) to achieve these properties. To workaround the practical difficulties when using these techniques - high computational cost for FHE and limited expressivity for VC, we leverage on transfer learning as a mean to (legitimately) decrease the footprint of encrypted domain calculations without jeopardizing the target security properties. In that sense, our approach demonstrates that scaling confidential and verifiable encrypted domain calculations to complex machine learning functions does not necessarily require scaling these techniques to the evaluation of large models. We furthermore demonstrate the practicality of our approach on an image classification task.

Paper Citation

in Harvard Style

Madi A., Stan O., Sirdey R. and Gouy-Pailler C. (2022). SecTL: Secure and Verifiable Transfer Learning-based inference. In Proceedings of the 8th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP, ISBN 978-989-758-553-1, pages 220-229. DOI: 10.5220/0010987700003120

in Bibtex Style

@conference{icissp22,
author={Abbass Madi and Oana Stan and Renaud Sirdey and Cédric Gouy-Pailler},
title={SecTL: Secure and Verifiable Transfer Learning-based inference},
booktitle={Proceedings of the 8th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,},
year={2022},
pages={220-229},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010987700003120},
isbn={978-989-758-553-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,
TI - SecTL: Secure and Verifiable Transfer Learning-based inference
SN - 978-989-758-553-1
AU - Madi A.
AU - Stan O.
AU - Sirdey R.
AU - Gouy-Pailler C.
PY - 2022
SP - 220
EP - 229
DO - 10.5220/0010987700003120