Adversarial Search Engine Optimization for Large Language Models
Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation Attacks, a new class of attacks that manipulate an LLM's selections to favor the attacker. We demonstrate that carefully crafted website content or plugin documentations can trick an LLM to promote the attacker products and discredit competitors, thereby increasing user traffic and monetization. We show this leads to a prisoner's dilemma, where all parties are incentivized to launch attacks, but the collective effect degrades the LLM's outputs for everyone. We demonstrate our attacks on production LLM search engines (Bing and Perplexity) and plugin APIs (for GPT-4 and Claude). As LLMs are increasingly used to rank third-party content, we expect Preference Manipulation Attacks to emerge as a significant threat.
Code (0)
등록된 구현이 없습니다.
Tasks
ChatbotMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
White Hat Search Engine Optimization using Large Language Models
We present novel white-hat search engine optimization techniques based on genAI and demonstrate their empirical merits.
Document RankingUnleashing the potential of prompt engineering for large language models
This comprehensive review delves into the pivotal role of prompt engineering in unleashing the capabilities of Large Language Models (LLMs). The development of Artificial Intelligence (AI), from its inception in the 1950…
HallucinationPrompt EngineeringPrompt LearningRanking Manipulation for Conversational Search Engines
Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM…
Conversational SearchLanguage ModelingLanguage ModellingLarge Language ModelAdversarial Representation Engineering: A General Model Editing Framework for Large Language Models
Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to int…
Generative Adversarial NetworkModel EditingEvaluating Robustness of Generative Search Engine on Adversarial Factual Questions
Generative search engines have the potential to transform how people seek information online, but generated responses from existing large language models (LLMs)-backed generative search engines may not always be accurate…
RetrievalRetrieval-augmented Generation