Fighting COVID-19 in the Dark: Methodology for Improved Inference Using Homomorphically Encrypted DNN

by   Moran Baruch, et al.

Privacy-preserving deep neural network (DNN) inference is a necessity in different regulated industries such as healthcare, finance, and retail. Recently, homomorphic encryption (HE) has been used as a method to enable analytics while addressing privacy concerns. HE enables secure predictions over encrypted data. However, there are several challenges related to the use of HE, including DNN size limitations and the lack of support for some operation types. Most notably, the commonly used ReLU activation is not supported under some HE schemes. We propose a structured methodology to replace ReLU with a quadratic polynomial activation. To address the accuracy degradation issue, we use a pre-trained model that trains another HE-friendly model, using techniques such as "trainable activation" functions and knowledge distillation. We demonstrate our methodology on the AlexNet architecture, using the chest X-Ray and CT datasets for COVID-19 detection. Our experiments show that by using our approach, the gap between the F1 score and accuracy of the models trained with ReLU and the HE-friendly model is narrowed down to within a mere 1.1 - 5.3 percent degradation.


page 1

page 2

page 3

page 4


On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks

Outsourcing neural network inference tasks to an untrusted cloud raises ...

Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning

Privacy concerns in client-server machine learning have given rise to pr...

Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approach

Deep learning (DL) is being increasingly utilized in healthcare-related ...

CryptoDL: Deep Neural Networks over Encrypted Data

Machine learning algorithms based on deep neural networks have achieved ...

Enabling Homomorphically Encrypted Inference for Large DNN Models

The proliferation of machine learning services in the last few years has...

nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data

In previous work, Boemer et al. introduced nGraph-HE, an extension to th...

Stabilizing Inputs to Approximated Nonlinear Functions for Inference with Homomorphic Encryption in Deep Neural Networks

Leveled Homomorphic Encryption (LHE) offers a potential solution that co...

Please sign up or login with your details

Forgot password? Click here to reset