PulseAugur
中
实时 07:30:30
English(EN) GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG

新的RAG框架使用同态加密增强隐私保护

研究人员开发了“GoldenRetriever”,一个利用非交互式同态加密的、用于隐私保护的检索增强生成(RAG)的新型框架。这种方法解决了通常以明文处理敏感数据的RAG系统的隐私问题。通过在加密下使用阈值选择而非昂贵的top-k排序,GoldenRetriever显著降低了延迟和计算复杂度。该系统使用基于CKKS的同态计算进行加密相似性评估和文档选择,确保查询内容和中间分数保持机密。实验表明,与之前的加密方法相比,其检索效果具有竞争力,延迟也大大降低,为更安全、可扩展的RAG应用铺平了道路。 AI

影响 增强了RAG系统的隐私性,可能使处理敏感数据的LLM得到更广泛的应用。

排序理由 该集群包含两篇arXiv论文,详细介绍了用于RAG系统的隐私保护检索的新型研究方法。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的RAG框架使用同态加密增强隐私保护

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
Research
该集群包含两篇arXiv论文,详细介绍了用于RAG系统的隐私保护检索的新型研究方法。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, safety, 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
69 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 [3]

  1. arXiv cs.CL TIER_1 English(EN) · Yang Gao, Gang Quan, Scott Piersall, Qian Lou, Dongdong Wang, Liqiang Wang ·

    GoldenRetriever:一种用于隐私保护RAG的非交互式同态加密检索

    arXiv:2607.29019v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, but existing pipelines typically operate on plaintext data, raising significant privacy concerns. Prior work on privacy-prese…

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Liqiang Wang ·

    GoldenRetriever:一种用于隐私保护RAG的非交互式同态加密检索

    Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, but existing pipelines typically operate on plaintext data, raising significant privacy concerns. Prior work on privacy-preserving retrieval leverages cryptographic techniques…

  3. arXiv cs.AI TIER_1 English(EN) · William Zerong Wang, Dongfang Zhao ·

    平衡隐私与效率:通过加性同态加密进行音乐信息检索

    arXiv:2508.07044v2 Announce Type: replace-cross Abstract: Modern music retrieval runs on vector embeddings, and once these embeddings are shared for search or matching they can be copied, probed, or used to train generative models. Fully homomorphic encryption can compute on them…