English(EN) Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models

大型语言模型为神经排序模型的新型对抗性攻击提供动力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-05 04:00

研究人员开发了一个名为 CRAFT 的新框架，用于攻击信息检索中使用的神经排序模型。该框架利用大型语言模型生成对抗性内容，然后用于微调和优化排序模型。实验表明，CRAFT 在各种排序架构中显著提高了对抗性推广率和排名提升效果，凸显了现实世界检索系统的潜在漏洞。 AI

影响凸显了生成式AI导致信息检索系统潜在漏洞的风险，促使人们需要更强大的防御措施。

排序理由这是一篇详细介绍攻击神经排序模型新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

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; 这是一篇详细介绍攻击神经排序模型新框架的研究论文。[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, 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: 144 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。

arXiv cs.CL TIER_1 English(EN) · Amin Bigdeli, Amir Khosrojerdi, Radin Hamidi Rad, Morteza Zihayat, Charles L. A. Clarke, Ebrahim Bagheri · 2026-05-05 04:00

误导诱导：针对神经排序模型的对抗性内容注入攻击

arXiv:2605.01591v1 Announce Type: cross Abstract: Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limiting effectiveness and transfera…