ROSETTA：通过混合 CKKS/TFHE 求值实现高效且准确的隐私保护 LLM 解码

Computer Science > Cryptography and Security arXiv:2609.16915 (cs) [Submitted on 15 Sep 2026] Title:ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation Authors:Jiangrui Yu, Baosheng Zhang, Liang Kong, Lin Ding, Yi Chen, Ye Yu, Mingzhe Zhang, Meng Li View a PDF of the paper titled ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation, by Jiangrui Yu and 7 other authors View PDF HTML (experimental) Abstract:Generative large language models (LLMs) have achieved state-of-the-art performance on many real-world tasks such as code generation and question answering. These models predominantly rely on an autoregressive decoding strategy that generates output tokens sequentially. However, their pervasive deployment raises serious privacy concerns, motivating private inference frameworks based on fully homomorphic encryption (FHE). A major limitation of existing FHE frameworks is their inefficiency in evaluating nonlinear operations, which incur substantial overhead and dominate the decode stage. In this paper, we propose ROSETTA, a hybrid CKKS/TFHE framework that overcomes this limitation. We first observe that nonlinear operations in the decode stage exhibit heterogeneous workload patterns, which can be handled effectively via a hybrid approach. We then realize this with two key contributions: 1) an adaptive segmented lookup-table protocol based on TFHE that enables efficient and accurate evaluation of nonlinear operations; and 2) a scheme-aware operator-selection framework that automatically assigns each nonlinear operator to CKKS or TFHE to minimize end-to-end decoding latency. We demonstrate that ROSETTA achieves up to $4.8\times$ Softmax speedup and $1.5$--$2.1\times$ end-to-end speedup over the SOTA framework CacheMir. Comments: Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2609.16915 [cs.CR] (or arXiv:2609.16915v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2609.16915 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Jiangrui Yu [view email] [v1] Tue, 15 Sep 2026 09:51:33 UTC (1,411 KB) Full-text links: Access Paper: View a PDF of the paper titled ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation, by Jiangrui Yu and 7 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR new | recent | 2026-09 Change to browse by: cs 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?)