Imperial College London
Alternate

ProfessorDanielRueckert

Faculty of Engineering, Department of Computing

Professor of Visual Information Processing
 
 
 
//

Contact

 

+44 (0)20 7594 8333d.rueckert Website

 
 
//

Location

 

568Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Haralampieva:2020:10.1145/3411501.3419432,
author = {Haralampieva, V and Rueckert, D and Passerat-Palmbach, J},
doi = {10.1145/3411501.3419432},
pages = {55--59},
publisher = {ACM},
title = {A systematic comparison of encrypted machine learning solutions for image classification},
url = {http://dx.doi.org/10.1145/3411501.3419432},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - This work provides a comprehensive review of existing frameworks based on secure computing techniques in the context of private image classification. The in-depth analysis of these approaches is followed by careful examination of their performance costs, in particular runtime and communication overhead.To further illustrate the practical considerations when using different privacy-preserving technologies, experiments were conducted using four state-of-the-art libraries implementing secure computing at the heart of the data science stack: PySyft and CrypTen supporting private inference via Secure Multi-Party Computation, TF-Trusted utilising Trusted Execution Environments and HE-Transformer relying on Homomorphic encryption.Our work aims to evaluate the suitability of these frameworks from a usability, runtime requirements and accuracy point of view. In order to better understand the gap between state-of-the-art protocols and what is currently available in practice for a data scientist, we designed three neural network architecture to obtain secure predictions via each of the four aforementioned frameworks. Two networks were evaluated on the MNIST dataset and one on the Malaria Cell image dataset. We observed satisfying performances for TF-Trusted and CrypTen and noted that all frameworks perfectly preserved the accuracy of the corresponding plaintext model.
AU  - Haralampieva,V
AU  - Rueckert,D
AU  - Passerat-Palmbach,J
DO  - 10.1145/3411501.3419432
EP  - 59
PB  - ACM
PY  - 2020///
SP  - 55
TI  - A systematic comparison of encrypted machine learning solutions for image classification
UR  - http://dx.doi.org/10.1145/3411501.3419432
UR  - https://dl.acm.org/doi/10.1145/3411501.3419432
UR  - http://hdl.handle.net/10044/1/84776
ER  -
Download