3 papers
cs.LG2026
The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision
Amman Yusuf, Jiwoo Shin, Ruizhi Deng +3
The Safety-Aware Denoiser (SAD) is a recent, training-free, safety-guidance framework for text diffusion models. During inference, SAD steers text samples toward safe regions of th…
cs.LG2025
Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models
Jiwoo Shin, Byeonghu Na, Mina Kang +2
Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address…
cs.LG2025
Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
Byeonghu Na, Mina Kang, Jiseok Kwak +6
Text-to-image models have recently made significant advances in generating realistic and semantically coherent images, driven by advanced diffusion models and large-scale web-crawl…