# Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions

arXiv: https://arxiv.org/abs/2408.05212 · HTML: https://mlsanity.com/paper/2408.05212/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2024.

## Built on by (most cited first, 15 of 15)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2412.16504/) (2024)
- [From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph](https://mlsanity.com/paper/2510.19873/) (2025)
- [RealHarm: A Collection of Real-World Language Model Application Failures](https://mlsanity.com/paper/2504.10277/) (2025)
- [Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models](https://mlsanity.com/paper/2506.10024/) (2025)
- [Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness](https://mlsanity.com/paper/2505.10845/) (2025)
- [Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond](https://mlsanity.com/paper/2410.18114/) (2024)
- [Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training](https://mlsanity.com/paper/2507.01752/) (2025)
- [Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning](https://mlsanity.com/paper/2509.05316/) (2025)
- [LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems](https://mlsanity.com/paper/2509.10682/) (2025)
- [A Privacy by Design Framework for Large Language Model-Based Applications for Children](https://mlsanity.com/paper/2602.17418/) (2026)
- [Curation of a Cardiology Interface Terminology for Highlighting Electronic Health Records using Machine Learning](https://mlsanity.com/paper/2606.08311/) (2026)
- [The Privacy-Hallucination Tradeoff in Differentially Private Language Models](https://mlsanity.com/paper/2609.00492/) (2026)
- [Privacy in Personalized AI Is a System Property, Not Just a Model Property](https://mlsanity.com/paper/2609.38289/) (2026)
- [Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII](https://mlsanity.com/paper/2610.06093/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy issues, which are exacerbated in critical domains (e.g., healthcare). Moreover, certain application-specific scenarios may require fine-tuning these models on private data. This survey critically examines the privacy threats associated with LLMs, emphasizing the potential for these models to memorize and inadvertently reveal sensitive information. We explore current threats by reviewing privacy attacks on LLMs and propose comprehensive solutions for integrating privacy mechanisms throughout the entire learning pipeline. These solutions range from anonymizing training datasets to implementing differential privacy during training or inference and machine unlearning after training. Our comprehensive review of existing literature highlights ongoing challenges, available tools, and future directions for preserving privacy in LLMs. This work aims to guide the development of more secure and trustworthy AI systems by providing a thorough understanding of privacy preservation methods and their effectiveness in mitigating risks.