Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

Authors: Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu, Zixuan Zhu, Mingxuan Liu, Baojun Liu, Mi Zhang, Min Yang | Published: 2026-03-26

2026.03.26

Authors: Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu, Zixuan Zhu, Mingxuan Liu, Baojun Liu, Mi Zhang, Min Yang
Published: 2026-03-26

Source: https://arxiv.org/abs/2603.25500

PDF: https://arxiv.org/pdf/2603.25500

AIにより推定されたラベル

モデル抽出攻撃大規模言語モデルプロンプトリーキング

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summarization. While these systems demonstrate improved efficiency over traditional search engines, their security implications against well-established black-hat Search Engine Optimization (SEO) attacks remain unexplored. In this paper, we present the first systematic study of SEO attacks targeting LLMSEs. Specifically, we examine ten representative LLMSE products (e.g., ChatGPT, Gemini) and construct SEO-Bench, a benchmark comprising 1,000 real-world black-hat SEO websites, to evaluate both open- and closed-source LLMSEs. Our measurements show that LLMSEs mitigate over 99.78