In a non-repeating multi-image setting, choosing typographic attack words by CLIP text-image similarity beats random matching on ImageNet and is claimed to transfer to InstructBLIP.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Typographic Attacks in a Multi-Image Setting
In a non-repeating multi-image setting, choosing typographic attack words by CLIP text-image similarity beats random matching on ImageNet and is claimed to transfer to InstructBLIP.