# On Protecting the Data Privacy of Large Language Models (LLMs): A Survey

arXiv: https://arxiv.org/abs/2403.05156 · HTML: https://mlsanity.com/paper/2403.05156/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2024.

## Built on by (most cited first, 30 of 96)

- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [A Survey on Data Synthesis and Augmentation for Large Language Models](https://mlsanity.com/paper/2410.12896/) (2024)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [A Survey of Useful LLM Evaluation](https://mlsanity.com/paper/2406.00936/) (2024)
- [A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare](https://mlsanity.com/paper/2502.15871/) (2025)
- [The Future of AI-Driven Software Engineering](https://mlsanity.com/paper/2406.07737/) (2024)
- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [A Survey on Privacy Risks and Protection in Large Language Models](https://mlsanity.com/paper/2505.01976/) (2025)
- [A Survey on Model Extraction Attacks and Defenses for Large Language Models](https://mlsanity.com/paper/2506.22521/) (2025)
- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection](https://mlsanity.com/paper/2408.02927/) (2024)
- [A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage](https://mlsanity.com/paper/2504.21035/) (2025)
- [Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI](https://mlsanity.com/paper/2407.21523/) (2024)
- [We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems](https://mlsanity.com/paper/2507.06250/) (2025)
- [Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches](https://mlsanity.com/paper/2404.12744/) (2024)
- [Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2412.16504/) (2024)
- [Towards User-level Private Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2502.17515/) (2025)
- [Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.19373/) (2025)
- [Efficient Prompting for LLM-based Generative Internet of Things](https://mlsanity.com/paper/2406.10382/) (2024)
- [LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states](https://mlsanity.com/paper/2411.19876/) (2024)
- [LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data](https://mlsanity.com/paper/2508.12158/) (2025)
- [From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph](https://mlsanity.com/paper/2510.19873/) (2025)
- [SafeLawBench: Towards Safe Alignment of Large Language Models](https://mlsanity.com/paper/2506.06636/) (2025)
- [Blockchain for Large Language Model Security and Safety: A Holistic Survey](https://mlsanity.com/paper/2407.20181/) (2024)
- [Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey](https://mlsanity.com/paper/2408.04643/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform writing, conversation, summarizing and other language tasks. When LLMs process and generate large amounts of data, there is a risk of leaking sensitive information, which may threaten data privacy. This paper concentrates on elucidating the data privacy concerns associated with LLMs to foster a comprehensive understanding. Specifically, a thorough investigation is undertaken to delineate the spectrum of data privacy threats, encompassing both passive privacy leakage and active privacy attacks within LLMs. Subsequently, we conduct an assessment of the privacy protection mechanisms employed by LLMs at various stages, followed by a detailed examination of their efficacy and constraints. Finally, the discourse extends to delineate the challenges encountered and outline prospective directions for advancement in the realm of LLM privacy protection.