收藏切换
Survey of Storage Mechanism Security Threats for Large Language Models
收藏切换
Liu Wang1, Shenao Wang2, Xinyi Hou2, Jian Zhao2, Rongxin Wu3, Qiao Xiang3, Yanjie Zhao2, Yi Wang1, *
Journal of Computer Research and Development | 2026, 63(3) : 640 - 667
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(3): 640-667
• Special Issue on Data Storage and Processing for New Quality Productive Forces •
Survey of Storage Mechanism Security Threats for Large Language Models
Full
Liu Wang1, Shenao Wang2, Xinyi Hou2, Jian Zhao2, Rongxin Wu3, Qiao Xiang3, Yanjie Zhao2, Yi Wang1, *
Affiliations
  • 1School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876
  • 2School of Cyberspace Security, Huazhong University of Science and Technology, Wuhan 430074
  • 3School of Informatics, Xiamen University, Xiamen, Fujian 361005
  • born in 1996. PhD. Student member of CCF. Her main research interest includes security and privacy preserving in the domain of mobile applications and artificial intelligence

    born in 2001. PhD candidate. His main research interests include static program analysis and open-source software security

    born in 2001. PhD candidate. Her main research interest includes security of large language model applications

    born in 2002. Master candidate. His main research interests include static program analysis and open-source software security

    born in 1987. PhD, associate professor, PhD supervisor. Member of CCF. His main research interests include software security, program analysis, and software engineering

    born in 1985. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include computer networks, formal methods, and intelligent systems

    born in 1996. PhD, postdoc. Member of CCF. Her main research interests include software system security, applications of LLMs in software engineering and software security, and security of LLM systems

    born in 1983. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software engineering, CSCW, and applied AI

About Author:

born in 1996. PhD. Student member of CCF. Her main research interest includes security and privacy preserving in the domain of mobile applications and artificial intelligence

born in 2001. PhD candidate. His main research interests include static program analysis and open-source software security

born in 2001. PhD candidate. Her main research interest includes security of large language model applications

born in 2002. Master candidate. His main research interests include static program analysis and open-source software security

born in 1987. PhD, associate professor, PhD supervisor. Member of CCF. His main research interests include software security, program analysis, and software engineering

born in 1985. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include computer networks, formal methods, and intelligent systems

born in 1996. PhD, postdoc. Member of CCF. Her main research interests include software system security, applications of LLMs in software engineering and software security, and security of LLM systems

born in 1983. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software engineering, CSCW, and applied AI

Published: 2026-03-01 doi: 10.7544/issn1000-1239.202550481
Outline
收藏切换

Large language models (LLMs), as a cornerstone technology in natural language processing (NLP), have demonstrated exceptional capabilities in text generation, information retrieval, and conversational systems. These models, such as ChatGPT, LLaMA, and Gemini, have been applied across various fields, including healthcare, education and finance, achieving near-human or even superhuman performance. However, with the widespread adoption of LLMs, their storage mechanisms face significant security and privacy risks throughout their lifecycle. Core storage modules, including model file storage, inference caching, and knowledge vector storage, support the functionality and efficiency of LLMs but also expose vulnerabilities and threats. For example, model file storage faces risks such as weight leakage and backdoor injection, inference caching is susceptible to side-channel attacks, and knowledge vector storage faces data poisoning and workflow hijacking. To address these emerging challenges, researchers have proposed defense strategies such as model encryption, backdoor detection, cache partitioning, and content filtering techniques. Although existing techniques have improved security to some extent, LLM storage technologies still face a range of critical challenges. This paper systematically reviews security risks and defense mechanisms for LLM storage across its lifecycle, focusing on attack surfaces and mitigation strategies. It identifies current limitations and highlights future research directions to enhance the security and reliability of LLM storage mechanisms.

large language model  /  model file storage  /  model inference cache  /  vector storage  /  security and privacy
王柳, 王申奥, 侯心怡, 赵建, 吴荣鑫, 向乔, 赵彦杰, 王祎. 大语言模型存储机制安全风险综述. 计算机研究与发展, 2026 , 63 (3) : 640 -667 . DOI: 10.7544/issn1000-1239.202550481
Liu Wang, Shenao Wang, Xinyi Hou, Jian Zhao, Rongxin Wu, Qiao Xiang, Yanjie Zhao, Yi Wang. Survey of Storage Mechanism Security Threats for Large Language Models[J]. Journal of Computer Research and Development, 2026 , 63 (3) : 640 -667 . DOI: 10.7544/issn1000-1239.202550481
Year 2026 volume 63 Issue 3
202
96
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550481
  • Receive Date:2025-06-17
  • Online Date:2026-11-06
  • Published:2026-03-01
Article Data
Affiliations
History
  • Received:2025-06-17
  • Revised:2025-09-05
  • Accepted:2025-10-11
Affiliations
    1School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876
    2School of Cyberspace Security, Huazhong University of Science and Technology, Wuhan 430074
    3School of Informatics, Xiamen University, Xiamen, Fujian 361005
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550481
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT