Detecting Hard-Coded Credentials in Software Repositories via LLMs
Digital Threats: Research and Practice · 30.09.2025 · 6 (3) · 1-16
DOI: 10.1145/3744756 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Threats: Research and Practice, online erschienen am 12.09.2025. Verfasst von Chidera Biringa und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 50 Literaturangaben.
Abstract (Originalsprache)
Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the software. These credentials create attack surfaces exploitable by a potential adversary to conduct malicious exploits, such as backdoor attacks. Recent detection efforts utilize embedding models to vectorize textual credentials before passing them to classifiers for predictions. However, these models struggle to discriminate between credentials with contextual and complex sequences resulting in high false-positive predictions. Context-dependent Pre-Trained Language Models (PLMs) or Large Language Models (LLMs) such as GPT tackled this drawback by leveraging the transformer neural architecture capacity for self-attention to capture contextual dependencies between words in input sequences. As a result, GPT has achieved wide success in several natural language understanding endeavors. Hence, we assess LLMs to represent these observations and feed extracted embedding vectors to a deep learning classifier to detect hard-coded credentials. Our model outperforms the current state of the art by 13% \(\in\) F1 measure on the benchmark dataset.
Zitieren
APA
Biringa, C., & Kul, G. (2025). Detecting Hard-Coded Credentials in Software Repositories via LLMs. Digital Threats: Research and Practice, 6(3), 1-16. https://doi.org/10.1145/3744756
Vancouver
Biringa C, Kul G. Detecting Hard-Coded Credentials in Software Repositories via LLMs. Digital Threats: Research and Practice. 2025;6(3):1-16. doi:10.1145/3744756
BibTeX
@article{Biringa2025,
author = {Biringa, Chidera and Kul, Gökhan},
title = {Detecting Hard-Coded Credentials in Software Repositories via LLMs},
journal = {Digital Threats: Research and Practice},
year = {2025},
volume = {6},
number = {3},
pages = {1--16},
doi = {10.1145/3744756}
}
EUVIMED