# Multimodal Pragmatic Jailbreak on Text-to-image Models

arXiv: https://arxiv.org/abs/2409.19149 · HTML: https://mlsanity.com/paper/2409.19149/

## Key facts

- Cited by 13 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 49 of its 86 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- 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 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)

## Built on by (most cited first, 13 of 13)

- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models](https://mlsanity.com/paper/2501.13772/) (2025)
- [Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models](https://mlsanity.com/paper/2412.05538/) (2024)
- [Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message](https://mlsanity.com/paper/2507.04673/) (2025)
- [Deep Research Agents Brings Deeper Harm](https://mlsanity.com/paper/2510.11851/) (2025)
- [The Illusion of Forgetting: Attack Unlearned Diffusion via Initial Latent Variable Optimization](https://mlsanity.com/paper/2602.00175/) (2026)
- [Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks](https://mlsanity.com/paper/2606.27147/) (2026)
- [Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM Framework](https://mlsanity.com/paper/2511.22943/) (2025)
- [Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models](https://mlsanity.com/paper/2604.05853/) (2026)
- [When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models](https://mlsanity.com/paper/2604.15967/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)
- [Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation](https://mlsanity.com/paper/2608.26535/) (2026)
- [TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak Attacks](https://mlsanity.com/paper/2609.31032/) (2026)

## Abstract (arXiv)

Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a novel type of jailbreak, which triggers T2I models to generate the image with visual text, where the image and the text, although considered to be safe in isolation, combine to form unsafe content. To systematically explore this phenomenon, we propose a dataset to evaluate the current diffusion-based text-to-image (T2I) models under such jailbreak. We benchmark nine representative T2I models, including two closed-source commercial models. Experimental results reveal a concerning tendency to produce unsafe content: all tested models suffer from such type of jailbreak, with rates of unsafe generation ranging from around 10% to 70% where DALLE 3 demonstrates almost the highest unsafety. In real-world scenarios, various filters such as keyword blocklists, customized prompt filters, and NSFW image filters, are commonly employed to mitigate these risks. We evaluate the effectiveness of such filters against our jailbreak and found that, while these filters may be effective for single modality detection, they fail to work against our jailbreak. We also investigate the underlying reason for such jailbreaks, from the perspective of text rendering capability and training data. Our work provides a foundation for further development towards more secure and reliable T2I models. Project page at https://multimodalpragmatic.github.io/.