SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
Researchers have developed SCI-Defense, a novel framework designed to counter manipulation attacks targeting LLM-based ranking systems. These attacks, known as Generative Engine Optimization (GEO), involve adversaries injecting misleading signals into product descriptions to artificially inflate their rankings. SCI-Defense integrates Perplexity detection, Semantic Integrity Scoring, and Inter-Candidate Detection to identify and block these manipulations. Evaluations on Amazon product descriptions and MS MARCO web passages demonstrated SCI-Defense's high precision and recall against various attack types, outperforming existing defense mechanisms. AI
IMPACT Introduces a new defense mechanism against sophisticated manipulation attacks targeting LLM-based ranking systems, potentially improving the reliability of search and recommendation engines.