Executable Program Feature Cleaning and Forgery Technology Based on Machine Learning

DOI: https://doi.org/10.62517/jbdc.202501202

Author(s)

Jiahong Wang, Yibo Chang*

Affiliation(s)

College of Electronic Engineering, National University of Defense Technology, Hefei, Anhui, China *Corresponding Author.

Abstract

As we delve into the digital age, the rapid evolution of information technology has brought about a surge in network security threats. Among the various tools used by cybercriminals, executable programs stand out as particularly potent vectors for malicious activities. The intricate nature of these programs means that their feature cleaning and forgery technologies are under intense scrutiny. Traditional methods of feature cleaning and forgery, while once effective, now face significant limitations in the face of the ever-evolving complexity of network security landscapes. In the last few years, machine learning has emerged as a groundbreaking force in cybersecurity, offering innovative solutions to the challenges posed by executable program threats. Our study introduces a novel approach to feature cleaning and forgery, grounded in the principles of machine learning. Through rigorous experimental verification, we have demonstrated that this method not only achieves high accuracy but also proves to be highly practical in the real-world application of feature cleaning and forgery. The aim of this research is to delve deeper into the feature cleaning and forgery technologies of executable programs, leveraging machine learning to pave the way for more robust and effective means of network security protection. The purpose of this study is to explore the cleaning and counterfeiting technology to provide effective means for network security protection.

Keywords

Machine Learning; Executable Program; Feature Cleaning; Forgery Technology; Network Security

References

[1] Xiaoyu Liu, Haichen Zhu. Research on New PE File Packer and Shelling Methods//International Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015). 2015-04-11. [2] Pillay, K.D.A. Relocating loader for MS-DOS. EXE executable files. Microprocessors and Microsystems, 1990, Vol.14(7): 427-434. [3] Christian Janiesch, Patrick Zschech, Kai Heinrich. Machine learning and deep learning. Electronic Markets, 2021, Vol. 31(3): 685-695. [4] T. Sangeetha, T. Meyappan, M. Phil. New Technique of Hidden Data in PE-File with in Unused Area Two. International Journal of Engineering Trends and Technology, 2012, Vol. 3(3): 304-310. [5] A. A. Zaidan, B. B. Zaidan, Shihab A. Hameed. Novel Approach for Secure Cover File of Hidden Data in the Unused Area within EXE File Using Computation between Cryptography and Steganography. International Journal of Computer Science & Network Security, 2009, Vol. 9(5): 294-300. [6] Madani, Houria, Ouerdi, et al. Ransomware: Analysis of Encrypted Files. International Journal of Advanced Computer Science and Applications, 2023, Vol. 14(1): 213-217. [7] Stanislav Igorevich Shterenberg, Andrey Vladimirovich Krasov, Igor Aleksandrovich Ushakov. Analysis of Using Equivalent Instructions at The Hidden Embedding of Information into the Executable Files. Journal of Theoretical and Applied Information Technology, 2015, Vol. 80(1): 28-34. [8] De Prado, Paula Martin. Machine learning. Biologist, 2024, Vol. 71(1): 8-9. [9] Lenover, Michael, Bedi, et al. Improvements to a Machine Learning Machining Feature Recognition System. Computer-Aided Design & Applications, 2025, Vol. 22(1): 119-135. [10] A. A. Zaidan, B. B. Zaidan, Hamid. A. Jalab. A New System for Hiding Data within (Unused Area Two + Image Page) of Portable Executable File using Statistical Technique and Advance Encryption Standared. International Journal of Computer Theory & Engineering, 2010, Vol. 2(2). [11] Nisha P. Shetty, Ikhil Ranjan. Using Steganography & Cryptography to Hide Data in EXE Files. International Journal of Engineering & Technology, 2018, Vol. 7.