A query-agnostic black-box attack uses zero-shot surrogate LLMs and adversarial learning on learnable queries to create transferable injection tokens that alter LLM retriever rankings.
Ranking manipulation for conversational search engines
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SCI-Defense combines perplexity detection, semantic integrity scoring across four manipulation dimensions, and inter-candidate detection to counter GEO attacks, reporting perfect precision on Amazon product data but domain-limited recall on web passages.
citing papers explorer
-
"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
A query-agnostic black-box attack uses zero-shot surrogate LLMs and adversarial learning on learnable queries to create transferable injection tokens that alter LLM retriever rankings.
-
SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
SCI-Defense combines perplexity detection, semantic integrity scoring across four manipulation dimensions, and inter-candidate detection to counter GEO attacks, reporting perfect precision on Amazon product data but domain-limited recall on web passages.