What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
cs.CV, cs.CR
Submitted: 2026-05-11
Updated: 2026-11-06
Code: https://github.com/bedapudi6788/NudeNet
Terminology
Sources
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
- Emerging Properties in Unified Multimodal Pretraining
- ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
- Prompt-to-Prompt Image Editing with Cross Attention Control
- Rethinking Negative Prompting for Concept Suppression: Unconditional Anchoring and Localized Guidance
- SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
- SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
- AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
- Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
- Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?
- Qwen-Image Technical Report
- When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance
- Show-o2: Improved Native Unified Multimodal Models
- SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
- Metaphor-based Jailbreak Attacks on Text-to-Image Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs