A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification
Haralampieva V, Rueckert D, Passerat-Palmbach J (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: Association for Computing Machinery, Inc
Pages Range: 55-59
Conference Proceedings Title: PPMLP 2020 - Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice
Event location: Virtual, Online, USA
ISBN: 9781450380881
Abstract
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.
Involved external institutions
Imperial College London / The Imperial College of Science, Technology and Medicine
United Kingdom (GB)
Technische Universität München (TUM)
Germany (DE)
United Kingdom (GB)
Technische Universität München (TUM)
Germany (DE)
How to cite
APA:
Haralampieva, V., Rueckert, D., & Passerat-Palmbach, J. (2020). A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification. In PPMLP 2020 - Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice (pp. 55-59). Virtual, Online, USA: Association for Computing Machinery, Inc.
MLA:
Haralampieva, Veneta, Daniel Rueckert, and Jonathan Passerat-Palmbach. "A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification." Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice, PPMLP 2020, Virtual, Online, USA Association for Computing Machinery, Inc, 2020. 55-59.
BibTeX: Download