Journal article · 2024 · Open access

A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly

Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, Yue Zhang

High-Confidence Computing, 4(2), 100211 · Published 29 February 2024 · DOI 10.1016/j.hcc.2024.100211

Open full textCite this paper

In brief

“A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly” is a 2024 journal article by Yifan Yao and 5 co-authors, published in High-Confidence Computing. OpenAlex counts 2,092 citations as of 19 November 2026, which puts it in the top 3% of works published in 2024 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at High-Confidence Computing.

Citations
2,092
Most cited in
2025 (964)
Field-weighted impact
172.15
References
356
Authors
6

Abstract

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

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

MLA 9

Yao, Yifan, et al. “A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly.” High-Confidence Computing, vol. 4, no. 2, 2024, p. 100211. https://doi.org/10.1016/j.hcc.2024.100211.

Chicago

Yao, Yifan, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, and Yue Zhang. 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.

Harvard

Yao, Y. et al. (2024) ‘A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly’, High-Confidence Computing, 4(2), p. 100211. doi:10.1016/j.hcc.2024.100211.

IEEE

Y. Yao, J. Duan, K. Xu, Y. Cai, Z. Sun, and Y. Zhang, “A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly,” High-Confidence Computing, vol. 4, no. 2, p. 100211, 2024, doi: 10.1016/j.hcc.2024.100211.

BibTeX

@article{yao2024survey,
  title     = {{A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly}},
  author    = {Yao, Yifan and Duan, Jinhao and Xu, Kaidi and Cai, Yuanfang and Sun, Zhibo and Zhang, Yue},
  journal   = {High-Confidence Computing},
  year      = {2024},
  volume    = {4},
  number    = {2},
  pages     = {100211},
  doi       = {10.1016/j.hcc.2024.100211},
  url       = {https://doi.org/10.1016/j.hcc.2024.100211}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202355
2024389389
2025964964
2026734734

Its field-weighted citation impact is 172.15: it has been cited 172.15 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • large language models
  • LLM security
  • code vulnerability detection
  • data confidentiality
  • LLM vulnerabilities
  • cybersecurity

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

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

How many times has this paper been cited?

2,092 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at High-Confidence Computing: sign in and open the full text from this page.

Who wrote this paper?

Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, Yue Zhang.

What is the DOI of this paper?

10.1016/j.hcc.2024.100211, permanently at https://doi.org/10.1016/j.hcc.2024.100211. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.