AI RESEARCH
Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
arXiv CS.CV
•
ArXi:2604.05853v1 Announce Type: new Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating images containing harmful textual payloads (e.g., fraudulent documents) embedded within visually benign scenes. Unlike traditional depictive jailbreaks that elicit visually objectionable imagery, inscriptive attacks weaponize the text-rendering capability itself.