Journal article · 2026 · Open access
Data security in large language models: risks, defense, and directions
Journal of King Saud University - Computer and Information Sciences, 38(7) · Published 25 August 2026 · DOI 10.1007/s44443-026-01200-9
In brief
“Data security in large language models: risks, defense, and directions” is a 2026 journal article by Kang Chen and 6 co-authors, published in Journal of King Saud University - Computer and Information Sciences. OpenAlex counts 2 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of King Saud University - Computer and Information Sciences.
- Citations
- 2
- Most cited in
- 2025 (1)
- Field-weighted impact
- 1.08
- References
- 125
- Authors
- 7
Abstract
Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often collected from diverse and uncurated sources, which exposes them to serious data security risks. Harmful or malicious data can compromise model behavior, leading to toxic outputs or hallucinations, while also creating vulnerabilities to data-driven attacks such as prompt injection and data poisoning. As LLMs continue to be integrated into critical real-world systems, understanding and addressing these data-centric security risks is imperative to safeguard user trust and system reliability. This survey offers a comprehensive overview of the main data security risks facing LLMs and reviews current defense strategies, including adversarial training, data cleaning, output guardrails, Reinforcement Learning from Human Feedback (RLHF), data augmentation, and Retrieval-Augmented Generation (RAG)/agent defenses. Additionally, we categorize and analyze relevant datasets used for assessing robustness and security across different domains, providing guidance for future research. Finally, we highlight key research directions that focus on data provenance and traceability, verifiable machine forgetting, secure model updates, standardized evaluation framework, explainability-driven security analysis, and effective governance frameworks, aiming to promote the safe and responsible development of LLM technology. This work seeks to inform researchers, practitioners, and policymakers, driving progress toward data security in LLMs.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chen, K., Zhou, X., Yu, Y., Lin, Y., Chen, H., Cai, C., & Shen, L. (2026). Data security in large language models: risks, defense, and directions. Journal of King Saud University - Computer and Information Sciences, 38(7). https://doi.org/10.1007/s44443-026-01200-9
MLA 9
Chen, Kang, et al. “Data security in large language models: risks, defense, and directions.” Journal of King Saud University - Computer and Information Sciences, vol. 38, no. 7, 2026. https://doi.org/10.1007/s44443-026-01200-9.
Chicago
Chen, Kang, Xiuze Zhou, Yuanhui Yu, Yuanguo Lin, Hefeng Chen, Congyu Cai, and Li Shen. 2026. “Data security in large language models: risks, defense, and directions.” Journal of King Saud University - Computer and Information Sciences 38 (7). https://doi.org/10.1007/s44443-026-01200-9.
Harvard
Chen, K. et al. (2026) ‘Data security in large language models: risks, defense, and directions’, Journal of King Saud University - Computer and Information Sciences, 38(7). doi:10.1007/s44443-026-01200-9.
IEEE
K. Chen et al., “Data security in large language models: risks, defense, and directions,” Journal of King Saud University - Computer and Information Sciences, vol. 38, no. 7, 2026, doi: 10.1007/s44443-026-01200-9.
BibTeX
@article{chen2026data,
title = {{Data security in large language models: risks, defense, and directions}},
author = {Chen, Kang and Zhou, Xiuze and Yu, Yuanhui and Lin, Yuanguo and Chen, Hefeng and Cai, Congyu and Shen, Li},
journal = {Journal of King Saud University - Computer and Information Sciences},
year = {2026},
volume = {38},
number = {7},
doi = {10.1007/s44443-026-01200-9},
url = {https://doi.org/10.1007/s44443-026-01200-9}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- large language models
- data security
- prompt injection
- data poisoning
- hallucinations
- adversarial training
- data cleaning
- reinforcement learning from human feedback
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Chen, K., Zhou, X., Yu, Y., Lin, Y., Chen, H., Cai, C., & Shen, L. (2026). Data security in large language models: risks, defense, and directions. Journal of King Saud University - Computer and Information Sciences, 38(7). https://doi.org/10.1007/s44443-026-01200-9
How many times has this paper been cited?
2 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 Journal of King Saud University - Computer and Information Sciences: sign in and open the PDF from this page.
Who wrote this paper?
Kang Chen, Xiuze Zhou, Yuanhui Yu, Yuanguo Lin, Hefeng Chen, Congyu Cai, Li Shen.
What is the DOI of this paper?
10.1007/s44443-026-01200-9, permanently at https://doi.org/10.1007/s44443-026-01200-9. 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.