EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Frequency-Domain Defense Framework for Adversarially Robust Wearable ECG Classification

Kehang Lai

Fundamental Scientific Reports in Multidisciplinary Areas · 31.07.2026 · 2 (3) · 1-13

DOI: 10.66238/fsrma117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fundamental Scientific Reports in Multidisciplinary Areas, online erschienen am 31.07.2026. Verfasst von Kehang Lai. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of different kinds of wearable devices, more and more people are using these systems monitoring their body signals. In addition, deep neural networks show strong performance when it comes to single-lead ECG rhythm classification. However, those machine learning classifiers can be easily affected by small deliberately designed adversarial perturbations to original input data. Hence, this essay proposes a lightweight frequency-domain defense framework for protecting a single-lead ECG classifier against adversarial perturbations using the MIT-BIH Arrhythmia Database. The experiment in this essay uses both patient-level train/test separation and continuous multi-beat ECG windows, so the evaluation is closer to a real-world clinical setting where new patients are unseen during training. This framework uses FGSM and PGD to attack an unprotected baseline model trained by time-series based 1D CNN (one-dimensional convolutional neural network) and a proposed frequency-domain trained 1D CNN defense model. In particular, the baseline receives normalized fixed length temporal windows, while the defense receives normalized FFT (Fast Fourier Transform) transformed frequency sequences. Also, both models are evaluated with the introduced adversarial attacks. Thus, across five random patient-level splits and 11 perturbation strengths, the result shows that the defense model achieved higher mean attacked macro F1 for all three attack families: 0.676 versus 0.419 for FGSM, 0.483 versus 0.248 for PGD, and 0.482 versus 0.248 for the combined attack. All in all, the main contribution in this essay is a lightweight framework that changes the classifier input from a temporal window to FFT-magnitude features and trains this frequency-domain model with clean, FGSM, and short-PGD samples. The code can be accessed at GitHub (https://github.com/ArcaneEmerald/ecg-defense-framework).

Zitieren

APA

Lai, K. (2026). A Lightweight Frequency-Domain Defense Framework for Adversarially Robust Wearable ECG Classification. Fundamental Scientific Reports in Multidisciplinary Areas, 2(3), 1-13. https://doi.org/10.66238/fsrma117

Vancouver

Lai K. A Lightweight Frequency-Domain Defense Framework for Adversarially Robust Wearable ECG Classification. Fundamental Scientific Reports in Multidisciplinary Areas. 2026;2(3):1-13. doi:10.66238/fsrma117

BibTeX
@article{Lai2026,
  author = {Lai, Kehang},
  title = {A Lightweight Frequency-Domain Defense Framework for Adversarially Robust Wearable ECG Classification},
  journal = {Fundamental Scientific Reports in Multidisciplinary Areas},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {1--13},
  doi = {10.66238/fsrma117}
}
Kostenlos starten →