AI RESEARCH
SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
arXiv CS.LG
•
ArXi:2605.21948v1 Announce Type: new LLM-based ranking systems are vulnerable to Generative Engine Optimization (GEO) attacks, where adversaries inject semantic signals into product descriptions to artificially boost rankings. We propose SCI-Defense, a three-component defense framework combining Perplexity detection (PPL), Semantic Integrity Scoring (SIS), and Inter-Candidate Detection (ICD). SIS evaluates four manipulation dimensions: Authority Attribution (AA), Narrative Purposiveness (NP), Comparative Claims (CA), and Temporal Claims (TC.