# Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge

arXiv: https://arxiv.org/abs/2309.11575 · HTML: https://mlsanity.com/paper/2309.11575/

## 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 11 of its 13 references that are in the map.
- First posted on arXiv 20 Sep 2023.

## 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, 11 of 11)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [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)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (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)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?](https://mlsanity.com/paper/2305.18398/) (2023)
- [Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models](https://mlsanity.com/paper/2305.14384/) (2023)

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

- [Latent Guard: a Safety Framework for Text-to-image Generation](https://mlsanity.com/paper/2404.08031/) (2024)
- [UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images](https://mlsanity.com/paper/2405.03486/) (2024)
- [LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models](https://mlsanity.com/paper/2406.05113/) (2024)
- [Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2407.15861/) (2024)
- [Replication in Visual Diffusion Models: A Survey and Outlook](https://mlsanity.com/paper/2408.00001/) (2024)
- [REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM](https://mlsanity.com/paper/2505.04673/) (2025)

## Abstract (arXiv)

Text-conditioned image generation models have recently achieved astonishing image quality and alignment results. Consequently, they are employed in a fast-growing number of applications. Since they are highly data-driven, relying on billion-sized datasets randomly scraped from the web, they also produce unsafe content. As a contribution to the Adversarial Nibbler challenge, we distill a large set of over 1,000 potential adversarial inputs from existing safety benchmarks. Our analysis of the gathered prompts and corresponding images demonstrates the fragility of input filters and provides further insights into systematic safety issues in current generative image models.