AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models

arXiv:2412.18123 · cs.CR, cs.CL · Submitted 2024-12-24 · Read on arXiv

cs.CR, cs.CL

Submitted: 2024-12-24

Updated: 2026-10-11

Comments: Accepted by TDSC 2026

Code: https://github.com/unitaryai/detoxify

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 2× in this paper · explained in 1 episode
• Data Augmentation — 1× in this paper · explained in 7 episodes

Sources

• Latent Guard: a Safety Framework for Text-to-image Generation
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• Harnessing LLM to Attack LLM-Guarded Text-to-Image Models
• SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
• Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
• SafeText: Safe Text-to-image Models via Aligning the Text Encoder
• AI Risk Management Should Incorporate Both Safety and Security

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs