Adversarial Search Engine Optimization for Large Language Models

Fredrik Nestaas, Edoardo Debenedetti, Florian Tramèr

Keywords: large language models, security, prompt injection, search engine optimization, function calling

TL;DR: We show that web pages and plugins can manipulate LLM systems for economic gains.

Abstract:

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 (a form of adversarial Search Engine Optimization).
We show this can lead to a _prisoner's dilemma_, where all parties are incentivized to launch attacks, but this collectively 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.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6195