On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts

Name: On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
Creator: NetApp; Helmholtz Center for Information Security; Netflix
Published: 2025-01-28T00:00:00+08:00

Zenodo2025-01-28 更新2026-04-07 收录

文本到图像模型安全

有害图像生成

数据链接：

https://zenodo.org/doi/10.5281/zenodo.14754526 数据链接链接失效反馈

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.

提供机构：

NetApp; Helmholtz Center for Information Security; Netflix

创建时间：

2025-01-28

On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts

资源简介：

相关数据集