Shudong Zhang

Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models

TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models

Attention! Your Vision Language Model Could Be Maliciously Manipulated

ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users