# ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System

arXiv: https://arxiv.org/abs/1901.03808 · HTML: https://mlsanity.com/paper/1901.03808/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2019.

## Built on by (most cited first, 10 of 10)

- [Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View](https://mlsanity.com/paper/2112.02625/) (2021)
- [ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2107.07677/) (2021)
- [GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction](https://mlsanity.com/paper/2208.01220/) (2022)
- [Application of Adversarial Examples to Physical ECG Signals](https://mlsanity.com/paper/2108.08972/) (2021)
- [ECG-ATK-GAN: Robustness against Adversarial Attacks on ECGs using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2110.09983/) (2021)
- [Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training](https://mlsanity.com/paper/2203.09487/) (2022)
- [Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems](https://mlsanity.com/paper/2401.17136/) (2024)
- [SoK: Security and Privacy Risks of Healthcare AI](https://mlsanity.com/paper/2409.07415/) (2024)
- [Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report](https://mlsanity.com/paper/2304.06286/) (2023)
- [Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices](https://mlsanity.com/paper/2506.15028/) (2025)

## Abstract (arXiv)

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.