# Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

arXiv: https://arxiv.org/abs/2505.21074 · HTML: https://mlsanity.com/paper/2505.21074/

## Key facts

- Cited by 8 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 51 of its 70 references that are in the map.
- First posted on arXiv 27 May 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, 30 of 51)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (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)
- [To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now](https://mlsanity.com/paper/2310.11868/) (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)
- [How Robust is Google's Bard to Adversarial Image Attacks?](https://mlsanity.com/paper/2309.11751/) (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)
- [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)
- [SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation](https://mlsanity.com/paper/2410.12761/) (2024)
- [FLIRT: Feedback Loop In-context Red Teaming](https://mlsanity.com/paper/2308.04265/) (2023)
- [A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion](https://mlsanity.com/paper/2303.16378/) (2023)
- [CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion](https://mlsanity.com/paper/2403.05121/) (2024)
- [Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models](https://mlsanity.com/paper/2404.02928/) (2024)

## Built on by (most cited first, 8 of 8)

- [Jailbreaking on Text-to-Video Models via Scene Splitting Strategy](https://mlsanity.com/paper/2509.22292/) (2025)
- [Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2602.03284/) (2026)
- [TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models](https://mlsanity.com/paper/2511.21145/) (2025)
- [Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information](https://mlsanity.com/paper/2603.03725/) (2026)
- [FERRET: Framework for Expansion Reliant Red Teaming](https://mlsanity.com/paper/2603.10010/) (2026)
- [RedEdit: Agentic Red-Teaming of Image Safety Classifiers via MCTS-Guided Photo-Editing](https://mlsanity.com/paper/2606.06140/) (2026)
- [ARENA: Automated Red-Teaming for Large Audio Language Models](https://mlsanity.com/paper/2608.15578/) (2026)
- [RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models](https://mlsanity.com/paper/2609.34920/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teaming is vital, yet white-box approaches are limited by their need for internal access, complicating their use with closed-source models. Moreover, existing black-box methods often assume knowledge about the model's specific defense mechanisms, limiting their utility in real-world commercial API scenarios. A significant challenge is how to evade unknown and diverse defense mechanisms. To overcome this difficulty, we propose a novel Rule-based Preference modeling Guided Red-Teaming (RPG-RT), which iteratively employs LLM to modify prompts to query and leverages feedback from T2I systems for fine-tuning the LLM. RPG-RT treats the feedback from each iteration as a prior, enabling the LLM to dynamically adapt to unknown defense mechanisms. Given that the feedback is often labeled and coarse-grained, making it difficult to utilize directly, we further propose rule-based preference modeling, which employs a set of rules to evaluate desired or undesired feedback, facilitating finer-grained control over the LLM's dynamic adaptation process. Extensive experiments on nineteen T2I systems with varied safety mechanisms, three online commercial API services, and T2V models verify the superiority and practicality of our approach.