When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts. While this paradigm greatly expands usability, it also introduces a critical and underexplored safety risk: the attack surface itself becomes visual. In this work, we propose Vision-Centric Jailbreak Attack (VJA), the first visual-to-visual jailbreak attack that conveys malicious instructions purely through visual inputs. To systematically study this emerging threat, we introduce IESBench, a safety-oriented benchmark for image editing models. Extensive experi...
| Authors | Jiacheng Hou, Yining Sun, Ruochong Jin et al. |
|---|---|
| Primary category | cs.CV |
| Published | 10 February 2026 |
| Last updated at source | 26 June 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- CSU-JPG/IESBenchDataset · cited by
Models and datasets referencing this paper
- CSU-JPG/IESBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 20 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.