The paper demonstrates that a tailored jailbreak method for querying groups of large models can achieve up to 100% success rate in some experiments on unprotected models, revealing overlooked multi-model safety risks.
Visual contextual at- tack: Jailbreaking mllms with image-driven context injec- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
New Wide-Net-Casting Jailbreak Attacks Risk Large Models
The paper demonstrates that a tailored jailbreak method for querying groups of large models can achieve up to 100% success rate in some experiments on unprotected models, revealing overlooked multi-model safety risks.