Xiaosen Wang

4

Papers

229

Total Citations

Papers (4)

MMA-Diffusion: MultiModal Attack on Diffusion Models

Boosting Adversarial Transferability by Block Shuffle and Rotation

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves