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.
ShieldLM: Empowering llms as aligned, trustworthy and responsible language models.arXiv preprint arXiv:2402.04269, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.