LLM 作为语言变色龙：解耦语义与结构以实现隐私保护通信

Computer Science > Cryptography and Security arXiv:2609.23193 (cs) [Submitted on 19 Sep 2026] Title:LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication Authors:Yuzhu Mao, Liang Zhao View a PDF of the paper titled LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication, by Yuzhu Mao and 1 other authors View PDF HTML (experimental) Abstract:As Large Language Model (LLM) APIs become increasingly integrated into privacy-sensitive workflows, ensuring inference-time privacy without compromising task utility remains a major challenge. Existing approaches preserve most of the original semantic content to maintain downstream performance, but this also leaves exploitable cues for reconstructing the original text. This work investigates semantic decoupling, which replaces original semantics with alternative content while preserving the structure needed for LLM reasoning. Based on this idea, we propose CROSS-MAP, a bidirectional framework that maps private inputs into a different semantic domain before inference and recovers the corresponding outputs afterward. Local models are trained with multi-objective optimization to maximize semantic divergence in the mapping stage while minimizing semantic inconsistency in the recovery stage. Experiments show that CROSS-MAP reduces reconstruction success across multiple attack settings while outperforming existing baselines in utility. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2609.23193 [cs.CR] (or arXiv:2609.23193v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2609.23193 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Yuzhu Mao [view email] [v1] Sat, 19 Sep 2026 19:41:29 UTC (431 KB) Full-text links: Access Paper: View a PDF of the paper titled LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication, by Yuzhu Mao and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR new | recent | 2026-09 Change to browse by: cs cs.AI cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)