English(EN) Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines

研究发现：LLM搜索引擎易受对抗性排名攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-10 04:00

一篇新的研究论文分析了基于大型语言模型的搜索引擎的对抗性攻击，将问题构建为无限重复的囚徒困境。该研究确定了可以维持合作的条件，并强调了攻击成本、贴现率和触发策略的影响。研究结果反直觉地表明，在某些情况下，降低攻击成功率可能会激励攻击，而限制成功率可能无效。 AI

影响强调了LLM信息检索系统复杂的安全挑战以及对适应性策略的需求。

排序理由在arXiv上发表的学术论文，详细介绍了对抗性攻击的理论分析。[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; 在arXiv上发表的学术论文，详细介绍了对抗性攻击的理论分析。[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: 136 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.AI TIER_1 English(EN) · Xiyang Hu · 2026-06-10 04:00

大型语言模型搜索引擎的对抗性攻击动态

arXiv:2501.00745v3 Announce Type: replace-cross Abstract: The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipul…