PulseAugur
中
实时 18:46:01
English(EN) SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning

SilentRetrieval 攻击通过投毒文档劫持 RAG 系统

研究人员开发了“SilentRetrieval”,这是一种旨在破坏检索增强生成 (RAG) 系统的新型两阶段攻击。该方法使用对抗性数据投毒注入经过处理的文档,这些文档在语义上得以保留且流畅,使其难以检测。该攻击在劫持各种基准测试和 LLM 的 RAG 输出方面取得了很高的成功率,即使在低投毒率下也是如此,尽管防御措施会以牺牲延迟为代价来减轻其有效性。 AI

影响 突出了 RAG 系统中的关键安全漏洞,可能影响 AI 生成内容的可靠性和可信度。

排序理由 该集群包含一篇详细介绍针对 RAG 系统的新型攻击方法的 ist 研究论文。

在 arXiv cs.IR (Information Retrieval) 阅读 →

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

SilentRetrieval 攻击通过投毒文档劫持 RAG 系统

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
该集群包含一篇详细介绍针对 RAG 系统的新型攻击方法的 ist 研究论文。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, safety
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
134 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) · Jiachen Qian ·

    SilentRetrieval:通过语义保留的对抗性数据投毒劫持检索增强生成

    arXiv:2605.28074v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversaria…

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Jiachen Qian ·

    SilentRetrieval:通过语义保留的对抗性数据投毒劫持检索增强生成

    Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted yet fluent documents. Stage 1 uses Coo…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    SilentRetrieval:通过语义保留的对抗性数据投毒劫持检索增强生成

    Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted yet fluent documents. Stage 1 uses Coo…