# DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization

arXiv: https://arxiv.org/abs/2408.11071 · HTML: https://mlsanity.com/paper/2408.11071/

## Key facts

- Cited by 22 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 24 of its 35 references that are in the map.
- First posted on arXiv 18 Aug 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, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [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)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (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)
- [Are Diffusion Models Vulnerable to Membership Inference Attacks?](https://mlsanity.com/paper/2302.01316/) (2023)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [QEBA: Query-Efficient Boundary-Based Blackbox Attack](https://mlsanity.com/paper/2005.14137/) (2020)
- [MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation](https://mlsanity.com/paper/2005.03161/) (2020)
- [ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization](https://mlsanity.com/paper/1910.06513/) (2019)
- [A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion](https://mlsanity.com/paper/2303.16378/) (2023)
- [DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training](https://mlsanity.com/paper/2310.02025/) (2023)
- [Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models](https://mlsanity.com/paper/2404.02928/) (2024)
- [Forget Unlearning: Towards True Data-Deletion in Machine Learning](https://mlsanity.com/paper/2210.08911/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval](https://mlsanity.com/paper/2103.02927/) (2021)
- [TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization](https://mlsanity.com/paper/2212.09254/) (2022)

## Built on by (most cited first, 22 of 22)

- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks](https://mlsanity.com/paper/2505.06679/) (2025)
- [T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models](https://mlsanity.com/paper/2504.15512/) (2025)
- [Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning](https://mlsanity.com/paper/2507.07139/) (2025)
- [Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models](https://mlsanity.com/paper/2504.11106/) (2025)
- [Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling](https://mlsanity.com/paper/2505.21074/) (2025)
- [RunawayEvil: Jailbreaking the Image-to-Video Generative Models](https://mlsanity.com/paper/2512.06674/) (2025)
- [Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks](https://mlsanity.com/paper/2607.07907/) (2026)
- [When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems](https://mlsanity.com/paper/2504.20376/) (2025)
- [Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models](https://mlsanity.com/paper/2508.03006/) (2025)
- [ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models](https://mlsanity.com/paper/2507.21985/) (2025)
- [MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models](https://mlsanity.com/paper/2601.07141/) (2026)
- [Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting](https://mlsanity.com/paper/2411.16769/) (2024)
- [ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models](https://mlsanity.com/paper/2602.00350/) (2026)
- [REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models](https://mlsanity.com/paper/2603.16576/) (2026)
- [STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack](https://mlsanity.com/paper/2605.00699/) (2026)
- [PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation](https://mlsanity.com/paper/2606.24081/) (2026)
- [Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models](https://mlsanity.com/paper/2607.17779/) (2026)
- [Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation](https://mlsanity.com/paper/2608.26535/) (2026)
- [The Temporal Moderation Gap: Text-to-Video Safety Filters Are Blind to Harm in Motion](https://mlsanity.com/paper/2609.26233/) (2026)
- [Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure](https://mlsanity.com/paper/2609.33445/) (2026)
- [Safe Image Generation via Reinforcement Learning](https://mlsanity.com/paper/2610.05908/) (2026)

## Abstract (arXiv)

Current text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images. To address this, various safety mechanisms and red teaming attack methods are proposed to enhance or expose the T2I model's capability to generate unsuitable content. However, many red teaming attack methods assume knowledge of the text encoders, limiting their practical usage. In this work, we rethink the case of textitpurely black-box attacks without prior knowledge of the T2l model. To overcome the unavailability of gradients and the inability to optimize attacks within a discrete prompt space, we propose DiffZOO which applies Zeroth Order Optimization to procure gradient approximations and harnesses both C-PRV and D-PRV to enhance attack prompts within the discrete prompt domain. We evaluated our method across multiple safety mechanisms of the T2I diffusion model and online servers. Experiments on multiple state-of-the-art safety mechanisms show that DiffZOO attains an 8.5% higher average attack success rate than previous works, hence its promise as a practical red teaming tool for T2l models.