# LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance

arXiv: https://arxiv.org/abs/2505.17145 · HTML: https://mlsanity.com/paper/2505.17145/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 58 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 26 of 26)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [On Protecting the Data Privacy of Large Language Models (LLMs): A Survey](https://mlsanity.com/paper/2403.05156/) (2024)
- [DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass](https://mlsanity.com/paper/2309.06746/) (2023)
- [THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption](https://mlsanity.com/paper/2206.00216/) (2022)
- [DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer](https://mlsanity.com/paper/2312.03724/) (2023)
- [Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services](https://mlsanity.com/paper/2305.06212/) (2023)
- [Privately Fine-Tuning Large Language Models with Differential Privacy](https://mlsanity.com/paper/2210.15042/) (2022)
- [Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection](https://mlsanity.com/paper/2309.03057/) (2023)
- [Just Fine-tune Twice: Selective Differential Privacy for Large Language Models](https://mlsanity.com/paper/2204.07667/) (2022)
- [Prompting Frameworks for Large Language Models: A Survey](https://mlsanity.com/paper/2311.12785/) (2023)
- [Privacy Preserving Prompt Engineering: A Survey](https://mlsanity.com/paper/2404.06001/) (2024)
- [LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers](https://mlsanity.com/paper/2305.18396/) (2023)
- [Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption](https://mlsanity.com/paper/2311.08610/) (2023)
- [Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models](https://mlsanity.com/paper/2402.02987/) (2024)
- [No Free Lunch Theorem for Privacy-Preserving LLM Inference](https://mlsanity.com/paper/2405.20681/) (2024)
- [The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts](https://mlsanity.com/paper/2406.14318/) (2024)
- [East: Efficient and Accurate Secure Transformer Framework for Inference](https://mlsanity.com/paper/2308.09923/) (2023)
- [Privacy Preserving Large Language Models: ChatGPT Case Study Based Vision and Framework](https://mlsanity.com/paper/2310.12523/) (2023)
- [Privacy-Preserving Language Model Inference with Instance Obfuscation](https://mlsanity.com/paper/2402.08227/) (2024)
- [ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets](https://mlsanity.com/paper/2407.02960/) (2024)
- [ConfusionPrompt: Practical Private Inference for Online Large Language Models](https://mlsanity.com/paper/2401.00870/) (2023)
- [Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography](https://mlsanity.com/paper/2501.08970/) (2025)
- [Transparency, Security, and Workplace Training & Awareness in the Age of Generative AI](https://mlsanity.com/paper/2501.10389/) (2024)

## Built on by (most cited first, 6 of 6)

- [A Survey on Model Extraction Attacks and Defenses for Large Language Models](https://mlsanity.com/paper/2506.22521/) (2025)
- [Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs](https://mlsanity.com/paper/2512.03994/) (2025)
- [From Performance to Purpose: A Sociotechnical Taxonomy for Evaluating Large Language Model Utility](https://mlsanity.com/paper/2602.20513/) (2026)
- [A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliance](https://mlsanity.com/paper/2603.09999/) (2026)
- [π-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Models](https://mlsanity.com/paper/2606.22153/) (2026)
- [A Human-LLM Teaming Framework for Privacy Risk Analysis: An Illustration with CBDC-Based Welfare Schemes](https://mlsanity.com/paper/2608.16461/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical concerns about data privacy and security, including the risk of sensitive data exposure. In this paper, we propose a security framework to enforce policy compliance and mitigate risks in LLM interactions. Our approach introduces three key innovations: (i) LLM-based policy enforcement: a customizable mechanism that enhances domain-specific detection of sensitive data. (ii) Dynamic policy customization: real-time policy adaptation and enforcement during user-LLM interactions to ensure compliance with evolving security requirements. (iii) Sensitive data anonymization: a format-preserving encryption technique that protects sensitive information while maintaining contextual integrity. Experimental results demonstrate that our framework effectively mitigates security risks while preserving the functional accuracy of LLM-driven tasks.