摘要
数字视频伪造被动取证技术直接依据已获得的视频数据本身来判别其真实性,具有更好的适应性,逐渐成为取证研究领域的主流。为了从整体上梳理与描述数字视频伪造被动取证技术,分析了常见的视频伪造操作的特点和它们遗留的痕迹以及对视频被动取证的影响,从取证手段和采用技术2个角度,归纳与总结了基于数字视频来源、基于视频篡改遗留痕迹、基于深度学习框架和基于原始视频特征表征等视频被动取证的典型方法,并详细地探讨了视频伪造被动取证领域面临的挑战和未来的发展趋势。
The video forgery passive forensics can directly distinguish the authenticity and integrity of the obtained video by utilizing the tampering traces without the aid of any prior axillary information such as digital watermark or perceptual hash signature. Thus, it has better adaptability and has become an important topic in the field of information security. In this survey, the characteristics of universal video forgery operations, their left tampered traces and influences to video passive forensics were in-depth analyzed. From two aspects of forensics strategy and techniques used, we discuss typical algorithms and methods in passive video forensics, including video source identification based, forgeries trails based, deep learning based, original video feature representation based techniques. Each of these categories of video forensics is summarized in detail, along with a critical analysis of the state of the art. The potential research directions and challenges of video passive forensics field are also investigated in detail.
作者
丁湘陵
杨高波
赵险峰
谷庆
熊义毛
DING Xiangling;YANG Gaobo;ZHAO Xianfeng;GU Qing;XIONG Yimao(School of Computer Science and Engineering,Hunan University of Science and Technology,Xiangtan,Hunan 411201,China;College of Computer and Communication,Hunan University,Changsha,Hunan 410082,China;State Key Laboratory of Information Security,Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100093,China;School of Cyber Security,University of Chinese Academy of Sciences,Beijing 100093,China;Guangdong Provincial Key Laboratory of Information Security Technology,Guangzhou,Guangdong 510000,China)
出处
《信号处理》
CSCD
北大核心
2021年第12期2371-2389,共19页
Journal of Signal Processing
基金
国家重点研发计划(2019QY2202,2020AAA0140000,2019QY(Y)0207)
湖南省自然科学基金面上项目(2020JJ4029)
信息安全国家重点实验室开放课题(2021-ZD-07)
广东省信息安全技术重点实验室开放基金(2020B1212060078)。
关键词
数字视频取证
被动取证
真实性鉴别
深度学习
digital video forensics
passive forensics
authentication verification
deep learning
