张洪蒙,,
毛秀青,
郭松,
胡永进
战略支援部队信息工程大学 郑州 450001
基金项目:国家重点研发计划(2017YFB0801900)
详细信息
作者简介:孙磊:男,1973年生,教授,主要研究方向为密码与系统安全、机器学习安全
张洪蒙:男,1995年生,硕士生,研究方向为计算机视觉
毛秀青:男,1980年生,副教授,主要研究方向为智能信息系统安全
郭松:男,1985年生,讲师,主要研究方向为计算机视觉
胡永进:男,1981年生,讲师,主要研究方向为网络信息防御
通讯作者:张洪蒙 meng19950929@stu.xjtu.edu.cn
中图分类号:TN911.73; TP309.2计量
文章访问数:1040
HTML全文浏览量:376
PDF下载量:96
被引次数:0
出版历程
收稿日期:2020-06-30
修回日期:2020-12-31
网络出版日期:2021-02-02
刊出日期:2021-10-18
Super-resolution Reconstruction Detection Method for DeepFake Hard Compressed Videos
Lei SUN,Hongmeng ZHANG,,
Xiuqing MAO,
Song GUO,
Yongjin HU
PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China
Funds:The National Key R&D Program of China (2017YFB0801900)
摘要
摘要:经典的深度伪造(DeepFake)视频检测方法一般使用卷积神经网络进行检测,但在强压缩深度伪造换脸视频数据集上表现较差,并会对真实数据做出大量误检测。针对这个问题,该文提出一种基于超分辨率重建的强压缩深度伪造视频检测方法。该方法基于深度神经网络检测模型,通过融入超分辨率重建技术,恢复强压缩视频所损失的空间与时间信息,进而提升对强压缩视频的检测准确率。使用FaceForensics++及DFDC数据集进行实验,针对强压缩的深度伪造视频,该方法较ResNet50提高了单帧以及视频的测试准确率,有效缓解强压缩真实视频的误检测问题。
关键词:深度伪造检测/
超分辨率重建/
强压缩视频/
深度学习
Abstract:The forensics methods of DeepFake video generally use convolution neural networks. However, these methods perform poorly on hard compressed DeepFake datasets and make a large number of false detections on real data. To solve the problem above, a method of hard compressed DeepFake video detection based on deep neural network model is proposed, which improves the detection accuracy of hard compressed video by incorporating super-resolution reconstruction technology and recovering the loss of the spatial and temporal information during hard compression. Experiments are performed with the FaceForensics++ Datasets and DFDC (the DeepFake Detection Challenge) Datasets for hard compressed DeepFake video, which improve the test accuracy of single frame and video compared to ResNet50, and effectively alleviate the problem of false detection of real video with hard compression.
Key words:DeepFake detection/
Super resolution reconstruction/
Video hard compression/
Deep learning
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=ec68cc87-2ff7-4f2a-b5a1-940030b79616