2 papers
cs.CV2025
Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models
Fan Yang, Yihao Huang, Jiayi Zhu +4
Diffusion-based text-to-image (T2I) models enable high-quality image generation but also pose significant risks of misuse, particularly in producing not-safe-for-work (NSFW) conten…
cs.CV2024
Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
Fan Yang, Yihao Huang, Kailong Wang +4
Vision-language pre-training (VLP) models, trained on large-scale image-text pairs, have become widely used across a variety of downstream vision-and-language (V+L) tasks. This wid…