Decorrelative Network Architecture for Robust Electrocardiogram Classification

07/19/2022
by   Christopher Wiedeman, et al.
9

Artificial intelligence has made great progresses in medical data analysis, but the lack of robustness and interpretability has kept these methods from being widely deployed. In particular, data-driven models are vulnerable to adversarial attacks, which are small, targeted perturbations that dramatically degrade model performance. As a recent example, while deep learning has shown impressive performance in electrocardiogram (ECG) classification, Han et al. crafted realistic perturbations that fooled the network 74 Current adversarial defense paradigms are computationally intensive and impractical for many high dimensional problems. Previous research indicates that a network vulnerability is related to the features learned during training. We propose a novel approach based on ensemble decorrelation and Fourier partitioning for training parallel network arms into a decorrelated architecture to learn complementary features, significantly reducing the chance of a perturbation fooling all arms of the deep learning model. We test our approach in ECG classification, demonstrating a much-improved 77.2 at least one correct network arm on the strongest adversarial attack tested, in contrast to a 21.7 require expensive optimization with adversarial samples, and thus can be scaled to large problems. These methods can easily be applied to other tasks for improved network robustness.

READ FULL TEXT

page 7

page 8

research
10/17/2021

ECG-ATK-GAN: Robustness against Adversarial Attacks on ECG using Conditional Generative Adversarial Networks

Recently deep learning has reached human-level performance in classifyin...
research
03/14/2022

Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training

In clinics, doctors rely on electrocardiograms (ECGs) to assess severe c...
research
09/30/2020

DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

Recent research finds CNN models for image classification demonstrate ov...
research
06/13/2019

A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks

The reliance on deep learning algorithms has grown significantly in rece...
research
01/12/2019

ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System

Deep neural networks (DNNs)-powered Electrocardiogram (ECG) diagnosis sy...
research
10/05/2020

Adversarial Boot Camp: label free certified robustness in one epoch

Machine learning models are vulnerable to adversarial attacks. One appro...
research
02/07/2023

RoNet: Toward Robust Neural Assisted Mobile Network Configuration

Automating configuration is the key path to achieving zero-touch network...

Please sign up or login with your details

Forgot password? Click here to reset