Deepfake Detection
Deepfake Detection
复制标题
深伪检测
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
M. Tejaggna
中科院分区：
文献类型：
--
作者：
R. Tejaswini;K. Rakesh;M. Veera;Mani Kanta;M. M. Reddy;M. Tejaggna
-面部图像生成和利用的迅速发展已经达到了引起社会和政治社会严重关注的地步。这导致了虚假信息和新信息的产生，最终导致人们对数字内容失去信任。我们开发了一个使用卷积神经网络（CNN）进行人脸检测和使用递归神经网络（RNN）进行视频分类的检测模型。尽管这项技术很了不起，但它也引发了社会和政治方面的担忧。到目前为止，借助发布的工具生成的深度假视频已被广泛用于制作假名人视频或复仇色情和假政治演讲等。政府机构已经在调查这些可能造成政治紧张局势的假视频问题。因此，有一个工具来检测这些虚假视频是至关重要的。（我们需要AI来对抗AI）
-The expeditious progress in facial image generation and exploitation has now come to a point where it raises serious concerns to the social and political society. This leads to the creation of fake information and new which ultimately results in loss of trust in digital content. We have developed a detection model using convolution neural network (CNN) for face detection and Recurrent neural network (RNN) for video classification. Even though this technology is remarkable it leads to social and political concerns. So far, with the help of released tools for the generation of deep fake videos have been widely used to create fake celebrity videos or revenge porn and fake political speeches, etc. Governmental entities are already looking into the issue of these fake videos which are likely to create political tensions. so, it is essential to have a tool for detecting these fake videos. (We need AI to fight an AI)
针对图像内容变化的深度特征插值
DOI：
--
发表时间：
2017
期刊：
CVPR 2017
影响因子：
--
作者：
Upchurch, P;Gardner, J;Pleiss, G;Pless, R;Snavely, N;Bala, K;Weinberger, K
通讯作者：
Weinberger, K