On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
收藏NIAID Data Ecosystem2026-05-02 收录
下载链接：
https://zenodo.org/record/14754525
下载链接
链接失效反馈官方服务：
资源简介：
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.
创建时间：
2025-01-28
