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

TL;DR

This paper introduces Semantic Encryption, a framework that transforms user inputs to protect privacy while preserving the logical structure and utility for cloud-based large language models, enabling secure and effective interactions.

Contribution

The paper proposes a novel Semantic Encryption framework with Semantic Encoding and Decoding components that maintain data utility and privacy during interactions with CLLMs.

Findings

SE effectively protects data privacy.

SE maintains data utility and user experience.

SE outperforms state-of-the-art methods like InferDPT.

Abstract

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.