Saved in:
Bibliographic Details
Main Authors: Chen, Dong, Yang, Tong, Zhai, Feipeng, Ouyang, Pengpeng, Liu, Qidong, Li, Yafei, Fu, Chong, Xu, Mingliang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01638
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908477030400000
author Chen, Dong
Yang, Tong
Zhai, Feipeng
Ouyang, Pengpeng
Liu, Qidong
Li, Yafei
Fu, Chong
Xu, Mingliang
author_facet Chen, Dong
Yang, Tong
Zhai, Feipeng
Ouyang, Pengpeng
Liu, Qidong
Li, Yafei
Fu, Chong
Xu, Mingliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01638
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic Encryption: Secure and Effective Interaction with Cloud-based Large Language Models via Semantic Transformation
Chen, Dong
Yang, Tong
Zhai, Feipeng
Ouyang, Pengpeng
Liu, Qidong
Li, Yafei
Fu, Chong
Xu, Mingliang
Cryptography and Security
Artificial Intelligence
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.
title Semantic Encryption: Secure and Effective Interaction with Cloud-based Large Language Models via Semantic Transformation
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2508.01638