SOURCE-LINKED INTELLIGENCE

Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image-text layout, while iterative attacks adapt only the image-text content with fixed attack strategies and frozen attacker parameters. We propose Meta-Adaptive Multimodal Jailbreaking (MAMJ), which instead optimizes the attacker itself along two axes: an attack strategy prompt (ASP) governing attack iteration and attacker model weights determining attack effectiveness. Across groups of multimodal at

Read original source ↗ Open in workspace

recordType

paper

region

Global