PE FAYLLARNING STATIK XUSUSIYATLARI ASOSIDA ZARARLI DASTURLARNI MODULLI ANSAMBL YORDAMIDA ANIQLASH
Turdimatov M. M. & Olimov F. F.
Annotatsiya
Maqolada Windows oilasiga mansub Portable Executable (PE) fayllarning statik xususiyatlari asosida zararli dasturlarni aniqlashga qaratilgan modulli ansambl yondashuvi ko‘rib chiqiladi. Tadqiqotda PE/header maydonlari, sectionlar statistikasi va entropiya, import va eksportga oid belgilar EMBER (v2) ma’lumotlar to‘plamidagi 2381 o‘lchamli xususiyatlar asosida uch mantiqiy blokka ajratildi. Birinchi blok uchun Random Forest, ikkinchi blok uchun XGBoost, uchinchi blok uchun esa LightGBM modeli tanlandi. Tajriba natijalari vaznli ansamblning 0.9567 F1-score va 0.9893 ROC-AUC, stacked ansamblning 0.9585 F1-score va 0.9915 ROC-AUC ko‘rsatkichlariga erishganini ko‘rsatdi. Olingan natijalar PE fayllarning strukturaviy va statistik xususiyatlarini alohida modullarda qayta ishlash hamda ularni ansambl darajasida birlashtirish statik aniqlashning aniqligi va barqarorligini oshirishini tasdiqlaydi.
Adabiyotlar
- Microsoft, “PE Format - Win32 apps,” Microsoft Learn, Jul. 14, 2025. [Online]. Manba: https://learn.microsoft.com/en-us/windows/win32/debug/pe-format
- H. S. Anderson and P. Roth, “EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models,” arXiv:1804.04637, 2018. [Online]. Manba: https://arxiv.org/abs/1804.04637
- L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [Online]. Manba: https://link.springer.com/article/10.1023/A:1010933404324
- T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proc. 22nd ACM SIGKDD, 2016, pp. 785–794. [Online]. Manba: https://doi.org/10.1145/2939672.2939785
- G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems 30, 2017. [Online]. Manba: https://proceedings.neurips.cc/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html
- M. I. Yousuf, M. A. A. Babar, and H. J. Al-Dulaimi, “Windows malware detection based on static analysis with machine learning methods,” PeerJ Computer Science, vol. 9, e1319, 2023. [Online]. Manba: https://peerj.com/articles/cs-1319/
- M. M.-H.-Z. Abedin and T. Mehrub, “Evaluating Ensemble and Deep Learning Models for Static Malware Detection with Dimensionality Reduction Using the EMBER Dataset,” arXiv:2507.16952, 2025. [Online]. Manba: https://arxiv.org/abs/2507.16952
- A. Verma, “An Optimized LightGBM Framework for Static Malware Detection,” Int. J. Comput. Sci. Machine Analytics, 2025. [Online]. Manba: https://submissions.adroidjournals.com/index.php/ijcma/article/view/208
- D. Gibert, C. Mateu, and J. Planes, “Assessing the impact of packing on static machine learning-based malware detection and classification systems,” Computers & Security, vol. 149, 104110, 2025. [Online]. Manba: https://doi.org/10.1016/j.cose.2025.104110