REVIEW 5 cited by
Adversarial Search Engine Optimization for Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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. 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.
Forward citations
Cited by 5 Pith papers
-
When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
The paper claims prompt compression is a new attack surface, but the abstract's COMA attack never appears in the body and the body's SoftCom requires white-box access.
-
Adversarial Attacks on Robotic Vision Language Action Models
Text-based adversarial suffixes can make OpenVLA robot policies elicit chosen target actions with over 90% success on one-hot targets and persist across rollout steps.
-
White Hat Search Engine Optimization using Large Language Models
LLM prompts that include past rankings produce document edits that improve retrieval ranking more than human students and a feature-based baseline, while keeping the text faithful.
-
Caption Injection for Optimization in Generative Search Engine
Adding VLM-generated, LLM-refined image captions into source text improves source visibility in generative search by about 1–2% relative, per the paper's G-Eval measurements on MRAMG.
-
Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics
Web-browsing LLMs can retrieve X profile content and infer demographics with above-chance accuracy in some cases, but the study's evidence is partly confounded by training-data memorization and a heavily reduced synth...
Discussion (0). Continue with ORCID to comment.