EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance Measurement and Analysis of Certifiable Defenses against Adversarial Patch Attacks

Zeyu Gao, Amin Saremi, Zonghua Gu

Journal of Signal Processing Systems · 2026-06 · 98 (1)

DOI: 10.1007/s11265-026-01989-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Signal Processing Systems, online erschienen am 17.03.2026. Verfasst von Zeyu Gao und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Umea University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We consider deep learning-based perception in real-time, safety-critical cyber-physical systems (CPS), such as autonomous driving and robotics, where embedded computing platforms typically operate under limited hardware resources due to SWaP-C (Size, Weight, Power, and Cost) constraints. In computer vision-based deep learning perception, adversarial patch attacks have emerged as a powerful method for deceiving classifiers. These attacks involve placing a carefully crafted patch on the input image, constituting a physically realizable and practical threat. Defense techniques against such attacks remain an active area of research. In this study, we evaluate and compare six well-known certifiable adversarial patch defenses, encompassing 14 models, across three different hardware platforms. We analyze their performance in terms of accuracy and processing time, highlighting key trade-offs. This paper aims to serve as a reference for selecting adversarial patch defense algorithms in real-time, safety-critical applications.

Förderung

  • Umea University

Zitieren

APA

Gao, Z., Saremi, A., & Gu, Z. (2026). Performance Measurement and Analysis of Certifiable Defenses against Adversarial Patch Attacks. Journal of Signal Processing Systems, 98(1). https://doi.org/10.1007/s11265-026-01989-8

Vancouver

Gao Z, Saremi A, Gu Z. Performance Measurement and Analysis of Certifiable Defenses against Adversarial Patch Attacks. Journal of Signal Processing Systems. 2026;98(1). doi:10.1007/s11265-026-01989-8

BibTeX
@article{Gao2026,
  author = {Gao, Zeyu and Saremi, Amin and Gu, Zonghua},
  title = {Performance Measurement and Analysis of Certifiable Defenses against Adversarial Patch Attacks},
  journal = {Journal of Signal Processing Systems},
  year = {2026},
  volume = {98},
  number = {1},
  doi = {10.1007/s11265-026-01989-8}
}
Kostenlos starten →