When the Editing Intent Is Split: A Cross-Modal Jailbreak Attack for Large Image Editing Models
arXiv:2610.23909v1 Announce Type: new Abstract: Large image editing models increasingly infer editing intent from both textual and visual inputs, creating an underexplored safety risk when harmful intent is distributed across modalities. In this work, we formalize this split-intent vulnerability an…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.CV
When the Editing Intent Is Split: A Cross-Modal Jailbreak Attack for Large Image Editing Models