USENIX2025@USD
Abstract
Disclaimer: To avoid any unnecessary ethical concerns, all NSFW content has been removed from this source. No NSFW content is included. Our goal is to prevent the generation and distribution of task-oriented NSFW content that may violate platform policies, not to provide the definition of NSFW content or enforce mandatory regulation for all scenarios. We encourage visitors to use this tool with a rational perspective.This repository is the official implementation of USD: NSFW Content Detection for Text-to-Image Models via Scene Graph.
Fields of Study & Subjects
Hate Speech and Cyberbullying Detection
Generative Adversarial Networks and Image Synthesis
Adversarial Robustness in Machine Learning
Publication details
- Journal / source
- Figshare
- Publication date
- 3 March 2026
- Language
- EN