SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Open Access
- 19 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2818-2832
Abstract
No abstract availableAll Related Versions
Funding Information
- the Natural Science Foundation of China (62372423, 62121002, 62072421)
- The National Research Foundation, Singapore under its National Large Language Models Funding Initiative (AISG-NMLP-2024-004)
- the National Research Foundation, Singapore under its AI Singapore Programme (AISG4-GC-2023-008-1B)
This publication has 14 references indexed in Scilit:
- Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution2024
- Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies2024
- Understanding Implosion in Text-to-Image Generative Models2024
- SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models2024
- ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models2024
- Diffusionics2024
- Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models2023
- Erasing Concepts from Diffusion Models2023
- Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?2022
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018