A grammar-tree and Monte Carlo search method automatically crafts prompts that can make synthetic portraits evade AIGC detectors, but the reported evidence is sparse and partly contradictory.
midjourney.com/home/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks
A grammar-tree and Monte Carlo search method automatically crafts prompts that can make synthetic portraits evade AIGC detectors, but the reported evidence is sparse and partly contradictory.