Dongdong Yang

AI Security Lab

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Deyue Zhang (1)Zonghao Ying (1)Jiankai Jin (1)Xiangzheng Zhang (1)

Papers (1)

Jul 20, 2026

AI Security LabJul 20, 2026·also Beihang

Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

MIND redefines adversarial prompt generation, achieving a staggering 95.62% success rate by intelligently interpreting model defenses rather than relying on brute-force tactics.

Dongdong Yang, Deyue Zhang, Zonghao Ying +3

Multimodal Models Red-Teaming & Adversarial Robustness

Search

Dongdong Yang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)