VisCRA jailbreaks multimodal LLMs by masking the most harmful image region and using a two-stage reasoning prompt to make the model infer and then comply.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models
VisCRA jailbreaks multimodal LLMs by masking the most harmful image region and using a two-stage reasoning prompt to make the model infer and then comply.