EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Robust CNN for Malware Classification against Executable Adversarial Attack

Yunchun Zhang, Jiaqi Jiang, Chao Yi, Hai Li, Shaohui Min, Ruifeng Zuo, Zhenzhou An, Yongtao Yu

Electronics · 05.03.2024 · 13 (5) · 989

DOI: 10.3390/electronics13050989 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 05.03.2024. Verfasst von Yunchun Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Opening Foundation of Yunnan Key Laboratory of Smart City in Cyberspace Security.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep-learning-based malware-detection models are threatened by adversarial attacks. This paper designs a robust and secure convolutional neural network (CNN) for malware classification. First, three CNNs with different pooling layers, including global average pooling (GAP), global max pooling (GMP), and spatial pyramid pooling (SPP), are proposed. Second, we designed an executable adversarial attack to construct adversarial malware by changing the meaningless and unimportant segments within the Portable Executable (PE) header file. Finally, to consolidate the GMP-based CNN, a header-aware loss algorithm based on the attention mechanism is proposed to defend the executive adversarial attack. The experiments showed that the GMP-based CNN achieved better performance in malware detection than other CNNs with around 98.61% accuracy. However, all CNNs were vulnerable to the executable adversarial attack and a fast gradient-based attack with a 46.34% and 34.65% accuracy decline on average, respectively. Meanwhile, the improved header-aware CNN achieved the best performance with an evasion ratio of less than 5.0%.

Förderung

  • Opening Foundation of Yunnan Key Laboratory of Smart City in Cyberspace Security

Zitieren

APA

Zhang, Y., Jiang, J., Yi, C., Li, H., Min, S., Zuo, R., An, Z., & Yu, Y. (2024). A Robust CNN for Malware Classification against Executable Adversarial Attack. Electronics, 13(5), 989. https://doi.org/10.3390/electronics13050989

Vancouver

Zhang Y, Jiang J, Yi C, Li H, Min S, Zuo R, et al. A Robust CNN for Malware Classification against Executable Adversarial Attack. Electronics. 2024;13(5):989. doi:10.3390/electronics13050989

BibTeX
@article{Zhang2024,
  author = {Zhang, Yunchun and Jiang, Jiaqi and Yi, Chao and Li, Hai and Min, Shaohui and Zuo, Ruifeng and An, Zhenzhou and Yu, Yongtao},
  title = {A Robust CNN for Malware Classification against Executable Adversarial Attack},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {5},
  pages = {989},
  doi = {10.3390/electronics13050989}
}
Infokarte | EUVIMED

Artikeldaten derzeit nicht verfügbar.

Recherche