Skip to content
Search
paperMarch 2024ReviewedOpen 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

View resourcePDF

Abstract

Comprehensive survey covering LLM security and privacy from three perspectives: beneficial applications of LLMs for security, attacks against LLMs, and defensive techniques.

Categories

Surveys
#survey#comprehensive#security-privacy

Framework mappings

OWASP Top 10 for LLM Applications
  • LLM01Prompt Injection
  • LLM02Sensitive Information Disclosure
  • LLM03Supply Chain
  • LLM04Data and Model Poisoning
MITRE ATLAS
  • AML.T0051LLM Prompt Injection
  • AML.T0054LLM Jailbreak

Cite

@article{yao2024survey,
  title = {{A Survey on Large Language Model (LLM) Security and Privacy: The Good, The Bad, and The Ugly}},
  author = {Yifan Yao and Jinhao Duan and Kaidi Xu and Yuanfang Cai and Zhibo Sun and Yue Zhang},
  year = {2024},
  month = mar,
  journal = {High-Confidence Computing},
  eprint = {2312.02003},
  archivePrefix = {arXiv},
  doi = {10.1016/j.hcc.2024.100211},
  url = {https://arxiv.org/abs/2312.02003}
}