Skip to content
Research

Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks.

arXiv:2610.07009v1 Announce Type: cross Abstract: Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-prompt StrongREJECT slice, us

arXiv cs.AIResearch source·