Xianlong Wang

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Multimodal Models (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Meng Xie (1)Li Zeng (1)Hangtao Zhang (1)Ziqi Zhou (1)

Papers (1)

Jul 27, 2026

TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models

Instruction-dense visual jailbreaks can covertly embed harmful instructions in images, bypassing safety measures that protect against direct text generation.

Meng Xie, Li Zeng, Hangtao Zhang +4

Constitutional AI & AI Ethics Multimodal Models Red-Teaming & Adversarial Robustness

Search

Xianlong Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)