A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluation Methods
Transactions on Artificial Intelligence · 2025
DOI: 10.53941/tai.2025.100003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions on Artificial Intelligence, 2025. Verfasst von Yihe Zhou und 3 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 208 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural language processing (NLP) performance, considering their widespread usage in many industries, including medicine, finance, education, etc., security concerns over their usage grow simultaneously. In recent years, the evolution of backdoor attacks has progressed with the advancement of defense mechanisms against them and more well-developed features in the LLMs. In this paper, we adapt the general taxonomy for classifying machine learning attacks on one of the subdivisions - training-time white-box backdoor attacks. Besides systematically classifying attack methods, we also consider the corresponding defense methods against backdoor attacks. By providing an extensive summary of existing works, we hope this survey can serve as a guideline for inspiring future research that further extends the attack scenarios and creates a stronger defense against them for more robust LLMs.
Zitieren
APA
Zhou, Y., Ni, T., Lee, W., & Zhao, Q. (2025). A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluation Methods. Transactions on Artificial Intelligence. https://doi.org/10.53941/tai.2025.100003
Vancouver
Zhou Y, Ni T, Lee W, Zhao Q. A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluation Methods. Transactions on Artificial Intelligence. 2025. doi:10.53941/tai.2025.100003
BibTeX
@article{Zhou2025,
author = {Zhou, Yihe and Ni, Tao and Lee, Wei-Bin and Zhao, Qingchuan},
title = {A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluation Methods},
journal = {Transactions on Artificial Intelligence},
year = {2025},
doi = {10.53941/tai.2025.100003}
}
EUVIMED