Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Lists
Only you see this
Abstract
[Update] Looking for a larger unsafe image dataset? We publish a new dataset named UnsafeBench on Hugging Face. Take a look at here! This dataset used in the paper https://arxiv.org/pdf/2305.13873.pdf contains four prompt sets and one image set. The four prompt sets were used to query Text-to-Image models and generate images for safety assessment. These sets include three harmful prompt sets and one harmless prompt set. The harmful prompts originate from different sources and contain various unsafe concepts, such as sexually explicit, violent, disturbing, hateful, and political content. Prompt Sets: 4chan Prompts: Harmful Lexica Prompts: Harmful Template Prompts: Harmful COCO Prompts: Harmless Image Dataset: This dataset consists of 800 images, which were randomly selected from all the generated images from Text-to-Image models. Safe: 580 images Sexually Explicit: 48 images Violent: 45 images Disturbing: 68 images Hateful: 35 images Political: 50 images
BibTeX
@inproceedings{qu2023unsafe,
author = {Yiting Qu and Xinyue Shen and Xinlei He and Michael Backes and Savvas Zannettou and Yang Zhang},
title = {{Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models}},
booktitle = {Zenodo},
year = {2023},
doi = {10.5281/zenodo.8255664},
}Loading related content...