# Wukong Framework for Not Safe For Work Detection in Text-to-Image systems

arXiv: https://arxiv.org/abs/2508.00591 · HTML: https://mlsanity.com/paper/2508.00591/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024)
- [Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?](https://mlsanity.com/paper/2202.06675/) (2022)
- [Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers](https://mlsanity.com/paper/2311.17717/) (2023)
- [A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion](https://mlsanity.com/paper/2303.16378/) (2023)
- [Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient](https://mlsanity.com/paper/2405.15304/) (2024)
- [GuardT2I: Defending Text-to-Image Models from Adversarial Prompts](https://mlsanity.com/paper/2403.01446/) (2024)
- [Understanding the Impact of Negative Prompts: When and How Do They Take Effect?](https://mlsanity.com/paper/2406.02965/) (2024)
- [ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users](https://mlsanity.com/paper/2405.19360/) (2024)
- [Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2407.15861/) (2024)
- [Stable Diffusion is Unstable](https://mlsanity.com/paper/2306.02583/) (2023)
- [Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion](https://mlsanity.com/paper/2308.02552/) (2023)

## Built on by (most cited first, 3 of 3)

- [FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding](https://mlsanity.com/paper/2604.07879/) (2026)
- [EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching](https://mlsanity.com/paper/2604.06063/) (2026)
- [Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation](https://mlsanity.com/paper/2609.19702/) (2026)

## Abstract (arXiv)

Text-to-Image (T2I) generation is a popular AI-generated content (AIGC) technology enabling diverse and creative image synthesis. However, some outputs may contain Not Safe For Work (NSFW) content (e.g., violence), violating community guidelines. Detecting NSFW content efficiently and accurately, known as external safeguarding, is essential. Existing external safeguards fall into two types: text filters, which analyze user prompts but overlook T2I model-specific variations and are prone to adversarial attacks; and image filters, which analyze final generated images but are computationally costly and introduce latency. Diffusion models, the foundation of modern T2I systems like Stable Diffusion, generate images through iterative denoising using a U-Net architecture with ResNet and Transformer blocks. We observe that: (1) early denoising steps define the semantic layout of the image, and (2) cross-attention layers in U-Net are crucial for aligning text and image regions. Based on these insights, we propose Wukong, a transformer-based NSFW detection framework that leverages intermediate outputs from early denoising steps and reuses U-Net's pre-trained cross-attention parameters. Wukong operates within the diffusion process, enabling early detection without waiting for full image generation. We also introduce a new dataset containing prompts, seeds, and image-specific NSFW labels, and evaluate Wukong on this and two public benchmarks. Results show that Wukong significantly outperforms text-based safeguards and achieves comparable accuracy of image filters, while offering much greater efficiency.