# Semantic Encryption: Secure and Effective Interaction with Cloud-based Large Language Models via Semantic Transformation

arXiv: https://arxiv.org/abs/2508.01638 · HTML: https://mlsanity.com/paper/2508.01638/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://mlsanity.com/paper/2311.04850/) (2023)
- [On Protecting the Data Privacy of Large Language Models (LLMs): A Survey](https://mlsanity.com/paper/2403.05156/) (2024)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [A Customized Text Sanitization Mechanism with Differential Privacy](https://mlsanity.com/paper/2207.01193/) (2022)
- [Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services](https://mlsanity.com/paper/2305.06212/) (2023)
- [Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection](https://mlsanity.com/paper/2309.03057/) (2023)
- [PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration](https://mlsanity.com/paper/2406.01394/) (2024)
- [Improving Large Models with Small models: Lower Costs and Better Performance](https://mlsanity.com/paper/2406.15471/) (2024)
- [DP-FP: Differentially Private Forward Propagation for Large Models](https://mlsanity.com/paper/2112.14430/) (2021)

## Abstract (arXiv)

The increasing adoption of Cloud-based Large Language Models (CLLMs) has raised significant concerns regarding data privacy during user interactions. While existing approaches primarily focus on encrypting sensitive information, they often overlook the logical structure of user inputs. This oversight can lead to reduced data utility and degraded performance of CLLMs. To address these limitations and enable secure yet effective interactions, we propose Semantic Encryption (SE)-a plug-and-play framework designed to preserve both privacy and utility. SE consists of two key components: Semantic Encoding and Semantic Decoding. In the encoding phase, a lightweight local model transforms the original user input into an alternative semantic context that maintains the original intent and logical structure while obfuscating sensitive information. This transformed input is then processed by the CLLM, which generates a response based on the transformed semantic context. To maintain a seamless user experience, the decoding phase will reconstruct the CLLM's response back into the original semantic context by referencing the locally stored user input. Extensive experimental evaluations demonstrate that SE effectively protects data privacy without compromising data utility or user experience, offering a practical solution for secure interaction with CLLMs. Particularly, the proposed SE demonstrates a significant improvement over the state-of-the-art InferDPT, surpassing it across various evaluated metrics and datasets.