隐式品牌注入：对抗性GEO的新威胁
原标题：Characterizing Adversarial GEO via Implicit Brand Injection
AI 摘要
研究者提出隐式品牌注入（IBI）多智能体框架，通过在文章中加入单句上下文融合的品牌提及，在不显促销的前提下影响生成式搜索引擎的检索与回答。团队构建了含1000篇文章、60个合成品牌、覆盖12个领域的IBIBench基准，并对比直接提示与Best-of-N基线。结果显示IBI在语义保持和困惑度扰动上更优，Hit@10最高达82.2%，品牌提及率与条件传播率分别达62.7%和75.9%，凸显生成式搜索中隐式内容操纵的防御需求。
正文节选
Characterizing Adversarial GEO via Implicit Brand Injection Abstract. Generative search engines increasingly shape how users discover products, services, and commercial entities by generating answers from retrieved web content. This creates an opportunity to influence which brands appear in these answers by modifying the content available to the retrieval system. In this work, we study an adversarial generative engine optimization (GEO) setting in which a predefined brand is added to an article