助推老大哥：利用编码攻击搜索引擎
Boosting Big Brother: Attacking Search Engines with Encodings
AI总结：
本文提出通过文本编码操纵攻击搜索引擎的索引与搜索，证明该攻击对Google、Bing、Elasticsearch及LLM聊天搜索等有效，并提供防御方案，警示其可被用于虚假信息活动。
摘要：
搜索引擎容易受到通过文本编码操纵针对索引和搜索的攻击。通过使用不常见的编码表示对文本进行难以察觉的扰动，对手可以针对特定搜索查询控制各搜索引擎的结果。我们证明，这种攻击对两大主要商业搜索引擎（Google 和 Bing）以及一款开源搜索引擎（Elasticsearch）均能成功实施。我们进一步证明，该攻击对 LLM 聊天搜索也能成功，包括 Bing 的 GPT-4 聊天机器人和 Google 的 Bard 聊天机器人。我们还提出了针对文本摘要和抄袭检测模型（两项与搜索密切相关的 ML 任务）的攻击变体。我们提供了一套防御这些技术的方法，并警告对手可利用这些攻击向毫无防备的用户发起虚假信息活动，这促使搜索引擎维护者需要对已部署系统进行修补。
英文摘要：
Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation. By imperceptibly perturbing text using uncommon encoded representations, adversaries can control results across search engines for specific search queries. We demonstrate that this attack is successful against two major commercial search engines - Google and Bing - and one open source search engine - Elasticsearch. We further demonstrate that this attack is successful against LLM chat search including Bing's GPT-4 chatbot and Google's Bard chatbot. We also present a variant of the attack targeting text summarization and plagiarism detection models, two ML tasks closely tied to search. We provide a set of defenses against these techniques and warn that adversaries can leverage these attacks to launch disinformation campaigns against unsuspecting users, motivating the need for search engine maintainers to patch deployed systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
