EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Malware Source Code Generation via Uncensored LLMs and Adversarial Evasion of Censored Model

Raúl Acosta-Bermejo, José Alexis Terrazas-Chavez, Eleazar Aguirre-Anaya

Applied Sciences · 22.08.2025 · 15 (17) · 9252

DOI: 10.3390/app15179252 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.08.2025. Verfasst von Raúl Acosta-Bermejo und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mexican Government through the Secretaría de Investigación y Posgrado of the Instituto Politécnico Nacional, México.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Malicious programs, commonly called malware, have had a pervasive presence in the world for nearly forty years and have continued to evolve and multiply exponentially. On the other hand, there are multiple research works focused on malware detection with different strategies that seem to work only temporarily, as new attack tactics and techniques quickly emerge. There are increasing proposals to analyze the problem from the attacker’s perspective, as suggested by MITRE ATT&CK. This article presents a proposal that utilizes Large Language Models (LLMs) to generate malware and understand its generation from the perspective of a red team. It demonstrates how to create malware using current models that incorporate censorship, and a specialized model is trained (fine-tuned) to generate code, enabling it to learn how to create malware. Both scenarios are evaluated using the pass@k metric and a controlled execution environment (malware lab) to prevent its spread.

Förderung

  • Mexican Government through the Secretaría de Investigación y Posgrado of the Instituto Politécnico Nacional, México

Zitieren

APA

Acosta-Bermejo, R., Terrazas-Chavez, J. A., & Aguirre-Anaya, E. (2025). Automated Malware Source Code Generation via Uncensored LLMs and Adversarial Evasion of Censored Model. Applied Sciences, 15(17), 9252. https://doi.org/10.3390/app15179252

Vancouver

Acosta-Bermejo R, Terrazas-Chavez JA, Aguirre-Anaya E. Automated Malware Source Code Generation via Uncensored LLMs and Adversarial Evasion of Censored Model. Applied Sciences. 2025;15(17):9252. doi:10.3390/app15179252

BibTeX
@article{AcostaBermejo2025,
  author = {Acosta-Bermejo, Raúl and Terrazas-Chavez, José Alexis and Aguirre-Anaya, Eleazar},
  title = {Automated Malware Source Code Generation via Uncensored LLMs and Adversarial Evasion of Censored Model},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {17},
  pages = {9252},
  doi = {10.3390/app15179252}
}
Kostenlos starten →