On the effectiveness of adversarial samples against ensemble learning-based windows PE malware detectors
International Journal of Information Security · 2025-02 · 24 (1)
DOI: 10.1007/s10207-024-00969-y ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Information Security, online erschienen am 10.01.2025. Verfasst von Trong-Nghia To und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Quỹ Đổi mới sáng tạo Vingroup, Viet Nam National University Ho Chi Minh City.
Abstract (Originalsprache)
The cybersecurity landscape is witnessing an increasing prevalence of threats and malicious programs, posing formidable challenges to conventional detection techniques. Although machine learning (ML) and deep learning (DL) have demonstrated effectiveness in malware detection, their susceptibility to adversarial attacks has led to a growing research trend. This study aims to provide a general framework that uses Reinforcement Learning and Explainable Artificial Intelligence (XAI) to generate and evaluate mutant Windows malware within the problem space. We concentrate on the three primary problems that arise while performing adversarial attacks on Windows Portable Executable malware, including format preservation, executability preservation, and maliciousness preservation. Additionally, we present an innovative approach called SHAPex to evaluate and clarify the impact of input feature predictions on malware detection predictions. This approach aims to optimize the application of results to future research efforts through three key questions pertaining to the predictive capacity of the ML/DL model. Experimental findings reveal that 100% of the selected mutation samples maintain their format integrity. Additionally, our system ensures the preservation of executable functionality in malware variants, yielding consistent and promising results. We have also encapsulated the analytical outcomes regarding the impact of input features on malware detectors’ prediction decisions within a specialized framework based on three research questions, emphasizing the predictive capacity of ML/DL models.
Förderung
- Quỹ Đổi mới sáng tạo Vingroup
- Viet Nam National University Ho Chi Minh City
Zitieren
APA
To, T., Kim, D. L., Hien, D. T. T., Khoa, N. H., Hoang, H. D., Duy, P. T., & Pham, V. (2025). On the effectiveness of adversarial samples against ensemble learning-based windows PE malware detectors. International Journal of Information Security, 24(1). https://doi.org/10.1007/s10207-024-00969-y
Vancouver
To T, Kim DL, Hien DTT, Khoa NH, Hoang HD, Duy PT, et al. On the effectiveness of adversarial samples against ensemble learning-based windows PE malware detectors. International Journal of Information Security. 2025;24(1). doi:10.1007/s10207-024-00969-y
BibTeX
@article{To2025,
author = {To, Trong-Nghia and Kim, Danh Le and Hien, Do Thi Thu and Khoa, Nghi Hoang and Hoang, Hien Do and Duy, Phan The and Pham, Van-Hau},
title = {On the effectiveness of adversarial samples against ensemble learning-based windows PE malware detectors},
journal = {International Journal of Information Security},
year = {2025},
volume = {24},
number = {1},
doi = {10.1007/s10207-024-00969-y}
}
EUVIMED