A Survey on Data Security in Large Language Models

TL;DR

This survey reviews data security risks in Large Language Models, discusses current defense strategies, analyzes datasets for robustness, and outlines future research directions for safer LLM deployment.

Contribution

It provides a comprehensive overview of data security challenges in LLMs, categorizes defense methods, and offers guidance for future research and policy development.

Findings

Identification of key data security risks in LLMs

Analysis of current defense strategies like adversarial training and RLHF

Guidance on datasets for robustness evaluation

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 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.