On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
From MaRDI portal
Dataset:6717275
DOI10.5281/zenodo.14754526Zenodo14754526MaRDI QIDQ6717275FDOQ6717275
Dataset published at Zenodo repository.
Yun Shen, Michael Backes, Yixin Wu, Yang Zhang, Ning Yu
Publication date: 28 January 2025
Copyright license: Creative Commons Attribution 4.0 International
Due to ethical considerations, the datasets for our paper, including the targeted hateful memes dataset (`data/toxic_images/`) and the poisoning datasets (`data/unsafe/`), are hosted on here with the request-access feature enabled.
This page was built for dataset: On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
