ForensicsSAM adds forgery- and adversary-specialized experts to the Segment Anything Model, claiming state-of-the-art forgery detection and localization that resists multiple attack methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack
ForensicsSAM adds forgery- and adversary-specialized experts to the Segment Anything Model, claiming state-of-the-art forgery detection and localization that resists multiple attack methods.