ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System

2019/01/12 by Huangxun Chen, Chen, Huangxun, Chenyu Huang +7 · 1 citation
Computer Science · Engineering · Medicine · #Adversarial Robustness in Machine Learning #Cardiac electrophysiology and arrhythmias #Electrostatic Discharge in Electronics #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1901.03808

openalex publication_date 2019/01/12 · openalex created_date 2019/01/25 · openalex updated_date 2026/07/28

Abstract

Deep neural networks (DNNs)-powered Electrocardiogram (ECG) diagnosis systems recently achieve promising progress to take over tedious examinations by cardiologists. However, their vulnerability to adversarial attacks still lack comprehensive investigation. The existing attacks in image domain could not be directly applicable due to the distinct properties of ECGs in visualization and dynamic properties. Thus, this paper takes a step to thoroughly explore adversarial attacks on the DNN-powered ECG diagnosis system. We analyze the properties of ECGs to design effective attacks schemes under two attacks models respectively. Our results demonstrate the blind spots of DNN-powered diagnosis systems under adversarial attacks, which calls attention to adequate countermeasures.

Citations

• Adam: A Method for Stochastic Optimization
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Soft-DTW: a Differentiable Loss Function for Time-Series
• Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
• Generating Adversarial Examples with Adversarial Networks
• Adversarial Attacks Against Medical Deep Learning Systems
• Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

Cited by

• Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices

Related

• Application of Adversarial Examples to Physical ECG Signals
• Defending Against Adversarial Attack in ECG Classification with\n Adversarial Distillation Training
• Improve robustness of DNN for ECG signal classification:a noise-to-signal ratio perspective
• Adversarial Examples for Electrocardiograms
• A Regularization Method to Improve Adversarial Robustness of Neural Networks for ECG Signal Classification