• Corpus ID: 239024647

A Regularization Method to Improve Adversarial Robustness of Neural Networks for ECG Signal Classification

  title={A Regularization Method to Improve Adversarial Robustness of Neural Networks for ECG Signal Classification},
  author={Linhai Ma and Liang Liang},
  • Linhai Ma, Liang Liang
  • Published 19 October 2021
  • Computer Science, Engineering
  • ArXiv
Electrocardiogram (ECG) is the most widely used diagnostic tool to monitor the condition of the human heart. By using deep neural networks (DNNs), interpretation of ECG signals can be fully automated for the identification of potential abnormalities in a patient's heart in a fraction of a second. Studies have shown that given a sufficiently large amount of training data, DNN accuracy for ECG classification could reach human-expert cardiologist level. However, despite of the excellent… 

Figures from this paper


Deep learning models for electrocardiograms are susceptible to adversarial attack
A method to construct smoothed adversarial examples for ECG tracings that are invisible to human expert evaluation is developed and it is shown that a deep learning model for arrhythmia detection from single-lead ECG 6 is vulnerable to this type of attack.
A deep convolutional neural network model to classify heartbeats
A 9-layer deep convolutional neural network (CNN) is developed to automatically identify 5 different categories of heartbeats in ECG signals to serve as a tool for screening of ECG to quickly identify different types and frequency of arrhythmicheartbeats.
ECG Heartbeat Classification: A Deep Transferable Representation
A method based on deep convolutional neural networks for the classification of heartbeats which is able to accurately classify five different arrhythmias in accordance with the AAMI EC57 standard is proposed.
Adversarial robustness study of convolutional neural network for lumbar disk shape reconstruction from MR images
Investigation of the in-distribution (IND) and out-of-dist distribution (OOD) adversarial robustness of a representative CNN for lumbar disk shape reconstruction from spine MR images shows thatIND adversarial training can improve the CNN robustness to IND adversarial attacks, and larger training datasets may lead to higher IND robustness.
Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
We develop an algorithm which exceeds the performance of board certified cardiologists in detecting a wide range of heart arrhythmias from electrocardiograms recorded with a single-lead wearable
Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks
A fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system that achieves a superior classification performance than most of the state-of-the-art methods for the detection of ventricular ectopic beats and supraventricular ectopy beats.
Opportunities and Challenges in Deep Learning Methods on Electrocardiogram Data: A Systematic Review
A systematic review of deep learning methods for ECG data from both modeling and application perspectives found that a hybrid architecture of a convolutional neural network and recurrent neural network ensemble using expert features yields the best results.
Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances
The computational methods reported in this review are a strong asset for medical discoveries and their translation to the clinical world may lead to promising advances.
Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization
This work suggests a theoretically inspired novel approach to improve the networks' robustness using the Frobenius norm of the Jacobian of the network, which is applied as post-processing, after regular training has finished and demonstrates empirically that it leads to enhanced robustness results with a minimal change in the original network's accuracy.
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
It is demonstrated that regularizing input gradients makes them more naturally interpretable as rationales for model predictions, and also exhibits robustness to transferred adversarial examples generated to fool all of the other models.