A Survey on Data Security in Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Kang, Zhou, Xiuze, Lin, Yuanguo, Su, Jinhe, Yu, Yuanhui, Shen, Li, Lin, Fan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916879638986752
author Chen, Kang
Zhou, Xiuze
Lin, Yuanguo
Su, Jinhe
Yu, Yuanhui
Shen, Li
Lin, Fan
author_facet Chen, Kang
Zhou, Xiuze
Lin, Yuanguo
Su, Jinhe
Yu, Yuanhui
Shen, Li
Lin, Fan
contents 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 issues such as toxic output, hallucinations, and vulnerabilities to threats such as prompt injection or 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, RLHF, and data augmentation. 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 secure model updates, explainability-driven defenses, and effective governance frameworks, aiming to promote the safe and responsible development of LLM technology. This work aims to inform researchers, practitioners, and policymakers, driving progress toward data security in LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey on Data Security in Large Language Models
Chen, Kang
Zhou, Xiuze
Lin, Yuanguo
Su, Jinhe
Yu, Yuanhui
Shen, Li
Lin, Fan
Cryptography and Security
Artificial Intelligence
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 issues such as toxic output, hallucinations, and vulnerabilities to threats such as prompt injection or 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, RLHF, and data augmentation. 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 secure model updates, explainability-driven defenses, and effective governance frameworks, aiming to promote the safe and responsible development of LLM technology. This work aims to inform researchers, practitioners, and policymakers, driving progress toward data security in LLMs.
title A Survey on Data Security in Large Language Models
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2508.02312