OpenRL/DeepFakeFace
收藏资源简介:
--- license: openrail task_categories: - image-to-image language: - en tags: - deepfake - diffusion model pretty_name: DeepFakeFace' --- ``` --- license: apache-2.0 --- ``` The dataset accompanying the paper "Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models". [[Website](https://sites.google.com/view/deepfakeface/home)] [[paper](https://arxiv.org/abs/2309.02218)] [[GitHub](https://github.com/OpenRL-Lab/DeepFakeFace)]. ### Introduction Welcome to the **DeepFakeFace (DFF)** dataset! Here we present a meticulously curated collection of artificial celebrity faces, crafted using cutting-edge diffusion models. Our aim is to tackle the rising challenge posed by deepfakes in today's digital landscape. Here are some example images in our dataset:  Our proposed DeepFakeFace(DFF) dataset is generated by various diffusion models, aiming to protect the privacy of celebrities. There are four zip files in our dataset and each file contains 30,000 images. We maintain the same directory structure as the IMDB-WIKI dataset where real images are selected. - inpainting.zip is generated by the Stable Diffusion Inpainting model. - insight.zip is generated by the InsightFace toolbox. - text2img.zip is generated by Stable Diffusion V1.5 - wiki.zip contains original real images selected from the IMDB-WIKI dataset. ### DeepFake Dataset Compare We compare our dataset with previous datasets here:  ### Experimental Results Performance of RECCE across different generators, measured in terms of Acc (%), AUC (%), and EER (%):  Robustness evaluation in terms of ACC(%), AUC (%) and EER(%):  ### Cite Please cite our paper if you use our codes or our dataset in your own work: ``` @misc{song2023robustness, title={Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models}, author={Haixu Song and Shiyu Huang and Yinpeng Dong and Wei-Wei Tu}, year={2023}, eprint={2309.02218}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```
数据集元信息如下: 许可证:OpenRail许可证 任务类别:图像到图像任务 语言:英语 标签:深度伪造(deepfake)、扩散模型(diffusion model) 展示名称:DeepFakeFace' 本数据集采用Apache 2.0开源许可证。 本数据集为论文《Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models》的配套数据集。[[网站](https://sites.google.com/view/deepfakeface/home)] [[论文](https://arxiv.org/abs/2309.02218)] [[GitHub仓库](https://github.com/OpenRL-Lab/DeepFakeFace)] ### 数据集介绍 欢迎使用**DeepFakeFace(DFF)**数据集!本数据集精心甄选了一批由前沿扩散模型生成的人工名人面部图像,旨在应对当前数字环境中日益严峻的深度伪造挑战。 以下为本数据集的部分示例图像:  我们提出的DeepFakeFace(简称DFF)数据集由多种扩散模型生成,旨在保护名人隐私。数据集共包含四个压缩包,每个压缩包内含30000张图像,目录结构与选取了真实图像的IMDB-WIKI数据集保持一致: - inpainting.zip:由Stable Diffusion Inpainting模型生成 - insight.zip:由InsightFace工具包生成 - text2img.zip:由Stable Diffusion V1.5生成 - wiki.zip:包含从IMDB-WIKI数据集中选取的原始真实图像 ### 深度伪造数据集对比 我们将本数据集与此前发布的数据集进行了对比:  ### 实验结果 以准确率(Acc,%)、AUC值(%)与等错误率(EER,%)为衡量指标,RECCE模型在不同生成器上的性能表现如下:  以ACC(%)、AUC (%)和EER(%)为评估指标的鲁棒性测试结果如下:  ### 引用说明 若您在研究工作中使用了本代码或数据集,请引用我们的论文: @misc{song2023robustness, title={Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models}, author={Haixu Song and Shiyu Huang and Yinpeng Dong and Wei-Wei Tu}, year={2023}, eprint={2309.02218}, archivePrefix={arXiv}, primaryClass={cs.CV} }
数据集概述
- 名称: DeepFakeFace (DFF)
- 许可证: Apache-2.0
- 任务类别: 图像到图像
- 语言: 英语
- 标签: 深度伪造, 扩散模型
- 描述: 该数据集包含使用扩散模型精心制作的名人假脸图像,旨在应对数字环境中深度伪造的挑战。
数据集内容
- 图像数量: 每个zip文件包含30,000张图像,共四个zip文件。
- 图像来源:
- inpainting.zip: 由Stable Diffusion Inpainting模型生成。
- insight.zip: 由InsightFace工具箱生成。
- text2img.zip: 由Stable Diffusion V1.5生成。
- wiki.zip: 包含从IMDB-WIKI数据集中选取的真实图像。
数据集结构
- 目录结构: 与IMDB-WIKI数据集的目录结构保持一致。
引用信息
-
论文:
@misc{song2023robustness, title={Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models}, author={Haixu Song and Shiyu Huang and Yinpeng Dong and Wei-Wei Tu}, year={2023}, eprint={2309.02218}, archivePrefix={arXiv}, primaryClass={cs.CV} }




