# SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models

arXiv: https://arxiv.org/abs/2510.05173 · HTML: https://mlsanity.com/paper/2510.05173/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Placed in

- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://mlsanity.com/paper/2305.14160/) (2023)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models](https://mlsanity.com/paper/2302.04222/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts](https://mlsanity.com/paper/2309.06135/) (2023)
- [Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?](https://mlsanity.com/paper/2202.06675/) (2022)
- [SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models](https://mlsanity.com/paper/2404.06666/) (2024)
- [GuardT2I: Defending Text-to-Image Models from Adversarial Prompts](https://mlsanity.com/paper/2403.01446/) (2024)
- [Prompt Stealing Attacks Against Text-to-Image Generation Models](https://mlsanity.com/paper/2302.09923/) (2023)
- [ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users](https://mlsanity.com/paper/2405.19360/) (2024)
- [SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution](https://mlsanity.com/paper/2309.14122/) (2023)
- [Exploring the Role of BERT Token Representations to Explain Sentence Probing Results](https://mlsanity.com/paper/2104.01477/) (2021)
- [Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies](https://mlsanity.com/paper/2408.07728/) (2024)
- [Influence Patterns for Explaining Information Flow in BERT](https://mlsanity.com/paper/2011.00740/) (2020)
- [GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models](https://mlsanity.com/paper/2408.12494/) (2024)
- [Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution](https://mlsanity.com/paper/2408.17285/) (2024)
- [Understanding Implosion in Text-to-Image Generative Models](https://mlsanity.com/paper/2409.12314/) (2024)

## Built on by (most cited first, 6 of 6)

- [TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks](https://mlsanity.com/paper/2605.01761/) (2026)
- [What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers](https://mlsanity.com/paper/2605.10180/) (2026)
- [VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts](https://mlsanity.com/paper/2604.06502/) (2026)
- [Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling](https://mlsanity.com/paper/2605.17971/) (2026)
- [Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers](https://mlsanity.com/paper/2605.30049/) (2026)
- [AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models](https://mlsanity.com/paper/2607.06120/) (2026)

## Abstract (arXiv)

Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce harmful content. Despite various defensive strategies, achieving robustness against attacks while maintaining practical utility in real-world applications remains a significant challenge. To address this issue, we first conduct an empirical study of the text encoder in the Stable Diffusion (SD) model, which is a widely used and representative text-to-image model. Our findings reveal that the [EOS] token acts as a semantic aggregator, exhibiting distinct distributional patterns between benign and adversarial prompts in its embedding space. Building on this insight, we introduce SafeGuider, a two-step framework designed for robust safety control without compromising generation quality. SafeGuider combines an embedding-level recognition model with a safety-aware feature erasure beam search algorithm. This integration enables the framework to maintain high-quality image generation for benign prompts while ensuring robust defense against both in-domain and out-of-domain attacks. SafeGuider demonstrates exceptional effectiveness in minimizing attack success rates, achieving a maximum rate of only 5.48% across various attack scenarios. Moreover, instead of refusing to generate or producing black images for unsafe prompts, SafeGuider generates safe and meaningful images, enhancing its practical utility. In addition, SafeGuider is not limited to the SD model and can be effectively applied to other text-to-image models, such as the Flux model, demonstrating its versatility and adaptability across different architectures. We hope that SafeGuider can shed some light on the practical deployment of secure text-to-image systems.