DeepAI AI Chat
Log In Sign Up

A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification

11/10/2020
by   Veneta Haralampieva, et al.
Imperial College London
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/23/2023

A Survey of Secure Computation Using Trusted Execution Environments

As an essential technology underpinning trusted computing, the trusted e...
05/28/2023

LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers

Prior works have attempted to build private inference frameworks for tra...
12/18/2020

NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-sourced Datasets

Training a machine learning model over an encrypted dataset is an existi...
09/28/2020

Oblivious Sampling Algorithms for Private Data Analysis

We study secure and privacy-preserving data analysis based on queries ex...
03/23/2023

Primer: Fast Private Transformer Inference on Encrypted Data

It is increasingly important to enable privacy-preserving inference for ...
06/16/2020

SPEED: Secure, PrivatE, and Efficient Deep learning

This paper addresses the issue of collaborative deep learning with priva...
11/24/2022

Beyond Mahalanobis-Based Scores for Textual OOD Detection

Deep learning methods have boosted the adoption of NLP systems in real-l...