EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adversarial Attacks with Defense Mechanisms on Convolutional Neural Networks and Recurrent Neural Networks for Malware Classification

Sharoug Alzaidy, Hamad Binsalleeh

Applied Sciences · 19.02.2024 · 14 (4) · 1673

DOI: 10.3390/app14041673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.02.2024. Verfasst von Sharoug Alzaidy und 1 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Imam Mohammad Ibn Saud Islamic University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the field of behavioral detection, deep learning has been extensively utilized. For example, deep learning models have been utilized to detect and classify malware. Deep learning, however, has vulnerabilities that can be exploited with crafted inputs, resulting in malicious files being misclassified. Cyber-Physical Systems (CPS) may be compromised by malicious files, which can have catastrophic consequences. This paper presents a method for classifying Windows portable executables (PEs) using Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs). To generate malware executable adversarial examples of PE, we conduct two white-box attacks, Jacobian-based Saliency Map Attack (JSMA) and Carlini and Wagner attack (C&W). An adversarial payload was injected into the DOS header, and a section was added to the file to preserve the PE functionality. The attacks successfully evaded the CNN model with a 91% evasion rate, whereas the RNN model evaded attacks at an 84.6% rate. Two defense mechanisms based on distillation and training techniques are examined in this study for overcoming adversarial example challenges. Distillation and training against JSMA resulted in the highest reductions in the evasion rates of 48.1% and 41.49%, respectively. Distillation and training against C&W resulted in the highest decrease in evasion rates, at 48.1% and 49.9%, respectively.

Förderung

  • Imam Mohammad Ibn Saud Islamic University

Zitieren

APA

Alzaidy, S., & Binsalleeh, H. (2024). Adversarial Attacks with Defense Mechanisms on Convolutional Neural Networks and Recurrent Neural Networks for Malware Classification. Applied Sciences, 14(4), 1673. https://doi.org/10.3390/app14041673

Vancouver

Alzaidy S, Binsalleeh H. Adversarial Attacks with Defense Mechanisms on Convolutional Neural Networks and Recurrent Neural Networks for Malware Classification. Applied Sciences. 2024;14(4):1673. doi:10.3390/app14041673

BibTeX
@article{Alzaidy2024,
  author = {Alzaidy, Sharoug and Binsalleeh, Hamad},
  title = {Adversarial Attacks with Defense Mechanisms on Convolutional Neural Networks and Recurrent Neural Networks for Malware Classification},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {4},
  pages = {1673},
  doi = {10.3390/app14041673}
}
Kostenlos starten →