EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Stealthy High-Impact Malicious Hardware Attacks on Deep Neural Networks

Maath Frman, Kholood J. Moulood, Mustafa Noori, Ekram H. Hasan, Oqbah Salim Atiyah, Qutaiba Alasad

Journal of Cybersecurity and Privacy · 30.06.2026 · 6 (4) · 112

DOI: 10.3390/jcp6040112 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cybersecurity and Privacy, online erschienen am 30.06.2026. Verfasst von Maath Frman und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of modern deep neural networks (DNNs) has played a crucial role in aiding humans across many real-world applications; yet, their hardware accelerators have been proven to be vulnerable to malicious attacks. One particularly severe and serious attack involves inserting a hardware Trojan (HT) into DNN accelerator hardware in order to enable attackers to stealthily manipulate model predictions during the supply chain. In this paper, we present a possible stealthy HT architecture that is difficult to detect and has a significant impact on the performance of DNN models. To successfully achieve this goal, we introduce the Sensitivity-Based Weight Selection (SBWS) algorithm, a novel technique that adapts machine learning (ML) sensitivity analysis to identify and modify a small number of weights that have the highest impact on DNN performance, compared to previous work. We evaluate the proposed attack on five DNN model tests (two distinct DNN models and four different datasets) using two designed payload types (weight zeroing and sign-flipping) and record the results based on various security metrics. The experimental results show average accuracy reductions of 26.7% for the zeroing attack and 48.1% for the sign-flipping attack, yielding an overall average of 37.4%, calculated over five independent runs per dataset with standard deviation

Zitieren

APA

Frman, M., Moulood, K. J., Noori, M., Hasan, E. H., Atiyah, O. S., & Alasad, Q. (2026). Robust Stealthy High-Impact Malicious Hardware Attacks on Deep Neural Networks. Journal of Cybersecurity and Privacy, 6(4), 112. https://doi.org/10.3390/jcp6040112

Vancouver

Frman M, Moulood KJ, Noori M, Hasan EH, Atiyah OS, Alasad Q. Robust Stealthy High-Impact Malicious Hardware Attacks on Deep Neural Networks. Journal of Cybersecurity and Privacy. 2026;6(4):112. doi:10.3390/jcp6040112

BibTeX
@article{Frman2026,
  author = {Frman, Maath and Moulood, Kholood J. and Noori, Mustafa and Hasan, Ekram H. and Atiyah, Oqbah Salim and Alasad, Qutaiba},
  title = {Robust Stealthy High-Impact Malicious Hardware Attacks on Deep Neural Networks},
  journal = {Journal of Cybersecurity and Privacy},
  year = {2026},
  volume = {6},
  number = {4},
  pages = {112},
  doi = {10.3390/jcp6040112}
}
Kostenlos starten →