A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
High-Confidence Computing · 2024-06 · 4 (2) · 100211
DOI: 10.1016/j.hcc.2024.100211 ↗Kurz gefasst
Fachartikel in der Zeitschrift High-Confidence Computing, 2024-06. Verfasst von Yifan Yao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1125-mal zitiert (Crossref) und nennt 353 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized natural language understanding and generation. They possess deep language comprehension, human-like text generation capabilities, contextual awareness, and robust problem-solving skills, making them invaluable in various domains (e.g., search engines, customer support, translation). In the meantime, LLMs have also gained traction in the security community, revealing security vulnerabilities and showcasing their potential in security-related tasks. This paper explores the intersection of LLMs with security and privacy. Specifically, we investigate how LLMs positively impact security and privacy, potential risks and threats associated with their use, and inherent vulnerabilities within LLMs. Through a comprehensive literature review, the paper categorizes the papers into"The Good"(beneficial LLM applications),"The Bad"(offensive applications), and"The Ugly"(vulnerabilities of LLMs and their defenses). We have some interesting findings. For example, LLMs have proven to enhance code security (code vulnerability detection) and data privacy (data confidentiality protection), outperforming traditional methods. However, they can also be harnessed for various attacks (particularly user-level attacks) due to their human-like reasoning abilities. We have identified areas that require further research efforts. For example, Research on model and parameter extraction attacks is limited and often theoretical, hindered by LLM parameter scale and confidentiality. Safe instruction tuning, a recent development, requires more exploration. We hope that our work can shed light on the LLMs' potential to both bolster and jeopardize cybersecurity.
Förderung
- National Science Foundation
Zitieren
APA
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024). A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly. High-Confidence Computing, 4(2), 100211. https://doi.org/10.1016/j.hcc.2024.100211
Vancouver
Yao Y, Duan J, Xu K, Cai Y, Sun Z, Zhang Y. A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly. High-Confidence Computing. 2024;4(2):100211. doi:10.1016/j.hcc.2024.100211
BibTeX
@article{Yao2024,
author = {Yao, Yifan and Duan, Jinhao and Xu, Kaidi and Cai, Yuanfang and Sun, Zhibo and Zhang, Yue},
title = {A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly},
journal = {High-Confidence Computing},
year = {2024},
volume = {4},
number = {2},
pages = {100211},
doi = {10.1016/j.hcc.2024.100211}
}
EUVIMED