摘要
深度学习作为机器学习的一个具有前景的重要分支,在计算机视觉方面取得了重大突破。深度伪造(Deepfake)通常指的是使用深度学习(deep learning)进行涉及人脸和人声的多媒体伪造技术,如果被恶意滥用会给社会带来灾难。深度伪造不仅限于面部的替换,还有修改面部特征、修改表情、唇形同步、姿势变换、完整脸生成、篡改音频到视频以及文本到视频等方式。人类面部在社会、政治、经济等方面的敏感性,使得深度伪造技术威胁着社会和个人的安全。对深度伪造产物进行检测也成为数字取证领域的一个重要研究课题。为了提供对Deepfake检测研究工作的最新概述,本文描述了各种针对解决Deepfake相关问题的处理方法。本文主要参考了谷歌学术检索2018—2022共5年的深度伪造论文,分为不同类别进行分析比较,并且详细介绍了深度伪造数据集的特点以及伪造方法,简述了深度伪造技术及其基本原理,介绍了检测器在深度伪造技术数据集上的性能效果,分别从输入维度、浅层特征和深层特针对深度伪造检测技术进行分类,并对未来发展前景进行展望。
Deep learning,a promising branch of machine learning,has made significant breakthroughs in computervision.However,Deepfake,which refers to the set of techniques for forging human-related multimedia data using deeplearning,can bring disasters to society if used maliciously.It is not only limited to facial replacement,but also othermanipulations,such as fabricating facial features,manipulating expressions,synchronizing lips,modifying head gestures,entire face synthesis,and tampering related audios to videos and related texts to videos.Moreover,it can be used to gener⁃ate faked pornographic videos or even faked speeches to subvert state power.Thus,deep forgery technology can greatlythreaten society and individuals,thereyby detecting Deepfake has also become an important research topic in digital foren⁃sics.We conducted a systematic and critical survey to provide an overview of the latest research on Deepfake detection by exploring the recent developments in Deepfake and related forensic techniques.This survey mainly referred to papers onDeepfake in Google Scholar during 2018—2022.This survey divided the Deepfake detection techniques into two categoriesfor analysis and comparison:input dimensions and forensic features.First,a comprehensive and systematic introduction ofdigital forensics is presented from the following aspects:1)the development and security of deep forgery detection technol⁃ogy,2)Deepfake technology architecture,and 3)the prevailing datasets and evaluation metrics.Then,this survey pres⁃ents Deepfake techniques in several categories.Finally,future challenges and development prospects are discussed.Interms of image and video effects,Deepfake techniques are usually divided into four categories:face replacement,lip syn⁃chronization,head puppets,and attribute modification.The most commonly used Deepfake algorithms are based on selfencoders,generative adversarial networks,and diffusion models.An typical autoencoder consists of two convolutional neu⁃ral networks acting as an encoder and a decod
作者
丁峰
匡仁盛
周越
孙珑
朱小刚
朱国普
Ding Feng;Kuang Rensheng;Zhou Yue;Sun Long;Zhu Xiaogang;Zhu Guopu(School of Software,Nanchang University,Nanchang 330047,China;School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150006,China;School of Public Policy and Administration,Nanchang University,Nanchang 330047,China;Jiangxi Institute of Interest of Things Industry Technology,Yingtan 335003,China)
出处
《中国图象图形学报》
CSCD
北大核心
2024年第2期295-317,共23页
Journal of Image and Graphics
基金
国家自然科学基金项目(62262041,62172402)
数据安全治理关键技术研究与应用项目(20224BBC41001)
江西省自然科学基金项目(20232BAB202011)。
关键词
深度造假
机器学习
人工智能
深度学习
数字取证
数字反取证
Deepfake
machine learning
artificial intelligence
deep learning
digital forensics
digital anti-forensics
