Română(RO) MOAI: Module-Optimizing Architecture for non-interactive secure transformer Inference

MOAI 框架通过优化的同态加密 (HE) 提升安全 Transformer 推理性能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员开发了 MOAI，一个旨在通过同态加密 (HE) 提高非交互式安全 Transformer 推理效率的新型框架。MOAI 通过优化评估流程、采用无旋转的 Softmax 和 LayerNorm 算法以及减少矩阵乘法中的 HE 旋转来解决 HE 的计算开销问题。与现有方法相比，这种方法显著缩短了评估时间，并在 BERT-base、Powerformer 和 LLaMA-3-8B 等模型上展示了潜在应用。 AI

影响通过显著降低同态加密的计算开销，增强了大型语言模型推理的隐私性。

排序理由该条目是一篇研究论文，详细介绍了用于安全 Transformer 推理的新技术框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

MOAI 框架通过优化的同态加密 (HE) 提升安全 Transformer 推理性能

本文如何被排名

Signal score: 37 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇研究论文，详细介绍了用于安全 Transformer 推理的新技术框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 Română(RO) · Linru Zhang, Xiangning Wang, Jun Jie Sim, Zhicong Huang, Jiahao Zhong, Huaxiong Wang, Pu Duan, Kwok-Yan Lam · 2026-11-11 05:00

MOAI：用于非交互式安全Transformer推理的模块优化架构

arXiv:2611.13641v1 Announce Type: cross Abstract: Privacy concerns have been raised in Large Language Models (LLM) inference when models are deployed in Cloud Service Providers (CSP). Homomorphic encryption (HE) offers a promising solution by enabling secure inference directly ov…

本文如何被排名

报道来源 [1]

MOAI：用于非交互式安全Transformer推理的模块优化架构

相关实体

相关话题