Yihao Huang

TISR: Breaking Vision–Language Models via Text–Image Segmentation and Reassembly

Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake

Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models

SAGE-CoT: Self-Adaptive Generated Chain-of-Thought for Jailbreaking

Analogy-based Multi-Turn Jailbreak against Large Language Models

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization

Time-variant Duo-image Inpainting via Interactive Distribution Transition Estimation