English(EN) FEnc$^2$: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding

新的FEnc2框架提升私有AI推理效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-16 04:00

研究人员开发了FEnc$^2$，这是一个旨在显著提高使用全同态加密（FHE）进行私有推理效率的新框架。该方法通过同时考虑卷积运算和网络架构来统一数据打包，以优化密文利用率并减少计算开销。在常见的图像识别任务中，FEnc$^2$在GPU上实现了高达228倍的端到端延迟缩减，在CPU上实现了高达226倍的延迟缩减。 AI

影响优化FHE以实现私有机器学习，可能促进更广泛的隐私保护AI应用的采用。

排序理由该集群包含一篇详细介绍用于提高AI推理效率的新技术框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍用于提高AI推理效率的新技术框架的研究论文。[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: 114 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Ran Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu, Fan Yao, Wujie Wen · 2026-06-16 04:00

FEnc$^2$：通过卷积和感知架构的碎片编码统一数据打包以实现高效的私有推理

arXiv:2606.16359v1 Announce Type: cross Abstract: Fully Homomorphic Encryption (FHE) enables privacy-preserving machine learning but incurs extreme computational and memory overhead. These costs come not only from expensive low-level primitives, including Number Theoretic Transfo…

本文如何被排名

报道来源 [1]

FEnc$^2$：通过卷积和感知架构的碎片编码统一数据打包以实现高效的私有推理

相关实体

相关话题