EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adversarial Attacks on Medical Image Classification

Min-Jen Tsai iD, Ping-Yi Lin, Ming-En Lee

Cancers · 23.08.2023 · 15 (17) · 4228

DOI: 10.3390/cancers15174228 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 23.08.2023. Verfasst von Min-Jen Tsai und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Management, National Yang Ming Chiao Tung University, Hsin-Chu 300, Taiwan. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Science Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the growing number of medical images being produced by diverse radiological imaging techniques, radiography examinations with computer-aided diagnoses could greatly assist clinical applications. However, an imaging facility with just a one-pixel inaccuracy will lead to the inaccurate prediction of medical images. Misclassification may lead to the wrong clinical decision. This scenario is similar to the adversarial attacks on deep learning models. Therefore, one-pixel and multi-pixel level attacks on a Deep Neural Network (DNN) model trained on various medical image datasets are investigated in this study. Common multiclass and multi-label datasets are examined for one-pixel type attacks. Moreover, different experiments are conducted in order to determine how changing the number of pixels in the image may affect the classification performance and robustness of diverse DNN models. The experimental results show that it was difficult for the medical images to survive the pixel attacks, raising the issue of the accuracy of medical image classification and the importance of the model’s ability to resist these attacks for a computer-aided diagnosis.

Schlagwörter

Stichwörter der Autor:innen

adversarial learningartificial intelligencecomputer visionmachine learningmetaheuristic

Autor:innen und Institutionen

  • Institute of Information Management, National Yang Ming Chiao Tung University, Hsin-Chu 300, Taiwan.

ORCID-Profile: Min-Jen Tsai

Förderung

  • The National Science Council

Zitieren

APA

Tsai, M. J., Lin, P. Y., & Lee, M. E. (2023). Adversarial Attacks on Medical Image Classification. Cancers, 15(17), 4228. https://doi.org/10.3390/cancers15174228

Vancouver

Tsai MJ, Lin PY, Lee ME. Adversarial Attacks on Medical Image Classification. Cancers. 2023;15(17):4228. doi:10.3390/cancers15174228

BibTeX
@article{Tsai2023,
  author = {Tsai, Min-Jen and Lin, Ping-Yi and Lee, Ming-En},
  title = {Adversarial Attacks on Medical Image Classification},
  journal = {Cancers},
  year = {2023},
  volume = {15},
  number = {17},
  pages = {4228},
  doi = {10.3390/cancers15174228}
}
Kostenlos starten →