作者： Zhang, Dengyong;Zhu, Wenjie;Ding, Xianglinrg;Yang, Gaobo;Li, Feng;...

期刊： Multimedia Tools and Applications,2023年82(10):14859-14877 ISSN：1380-7501

通讯作者： Ding, Xiangling(xianglingding@163.com)

作者机构： [Deng, Zelin; Zhu, Wenjie; Song, Yun; Li, Feng; Zhang, Dengyong] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha 410004, Hunan, Peoples R China.;[Deng, Zelin; Zhu, Wenjie; Song, Yun; Li, Feng; Zhang, Dengyong] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410004, Hunan, Peoples R China.;[Ding, Xianglinrg] Hunan Univ Sci & Technol, Sch Comp & Commun Engn, Xiangtan 411201, Hunan, Peoples R China.;[Ding, Xianglinrg] Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing 100093, Peoples R China.;[Ding, Xianglinrg] Guangdong Prov Key Lab Informat Secur Technol, Guangzhou 51000, Guangdong, Peoples R China.

通讯机构： [Xiangling Ding] S;School of Computer and Communication Engineering, Hunan University of Science and Technology, Xiangtan, China<&wdkj&>State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China<&wdkj&>Guangdong Provincial Key Laboratory of Information Security Technology, Guangzhou, China

关键词： Extraction;Feature extraction;Deepfake;Detection networks;Extraction algorithms;Internet technology;Key feature;Neural-networks;Public dataset;Residual domain;Spatial domains;Two-stream;High pass filters

摘要： With the rapid development of Internet technology, the Internet is full of false information, and Deepfakes, as a kind of visual forgery content, brings the greatest impact to people. The existing mainstream Deepfakes public datasets often have millions of frames, and if the first N frames are used to train the model some key features may be lost. If all frames are used, the model is easily overfitted and training often takes several days, which greatly consumes computational resources. Therefore, we propose an adaptive video frame extraction algorithm to extract the required number of frames from all video frames. The algorithm is able to reduce data redundancy and increase feature richness. In addition, we design a two-stream Deepfakes detection network SRTNet by combining the image spatial domain and residual domain, which consists of spatial-stream and residual-stream. The spatial-stream uses the original RGB image as input to capture high-level tampering artifacts. Residual-stream uses three sets of high-pass filters to process the input image to obtain the image residuals to capture the tampering traces. Two-stream parallel training, and the features are concatenated to enable the model to capture tamper features from both spatial and residual domains to achieve better detection performance. The experimental results show that the proposed adaptive frame extraction algorithm can improve the model performance. And the proposed detection network SRTNet achieves better results than previous work on mainstream Deepfake dataset. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

语种： 英文

作者： Zhang, Dengyong;Wu, Pengjie;Li, Feng;Zhu, Wenjie;Sheng, Victor S.

期刊： KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS,2022年16(5):1671-1686 ISSN：1976-7277

通讯作者： Li, F.

作者机构： [Zhu, Wenjie; Li, Feng; Wu, Pengjie; Zhang, Dengyong] Changsha Univ Sci & Technol, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha 410114, Peoples R China.;[Zhu, Wenjie; Li, Feng; Wu, Pengjie; Zhang, Dengyong] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.;[Sheng, Victor S.] Texas Tech Univ, Dept Comp Sci, Lubbock, TX 79409 USA.

通讯机构： Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha, China

关键词： Classification (of information);Face recognition;Learning systems;Deepfake detection;Face manipulation;Identity information;Learning technology;Machine-learning;Manipulation tools;Pixelhop++;Subspace learning;Successive subspace learning;Video detection;Deep learning

摘要： Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models. Copyright © 2022 KSII.

语种： 英文

作者： Ding, Xiangling;Zhu, Wenjie;Zhang, Dengyong

期刊： Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks workshops,2022年2022-September:425-433 ISSN：2155-5486

作者机构： [Ding, Xiangling] Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan, Peoples R China.;[Ding, Xiangling] Guangdong Key Lab Intelligent Informat Proc, Shenzhen, Peoples R China.;[Ding, Xiangling] Shenzhen Key Lab Media Secur, Shenzhen, Peoples R China.;[Ding, Xiangling] Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing, Peoples R China.;[Ding, Xiangling] Zhengzhou Xinda Inst Adv Technol, Zhengzhou, Peoples R China.

会议名称： 19th Annual IEEE International Conference on Sensing, Communication, and Networking (IEEE SECON)

会议时间： SEP 20-23, 2022

会议地点： ELECTR NETWORK

会议主办单位： [Ding, Xiangling] Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan, Peoples R China.^[Ding, Xiangling] Guangdong Key Lab Intelligent Informat Proc, Shenzhen, Peoples R China.^[Ding, Xiangling] Shenzhen Key Lab Media Secur, Shenzhen, Peoples R China.^[Ding, Xiangling] Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing, Peoples R China.^[Ding, Xiangling] Zhengzhou Xinda Inst Adv Technol, Zhengzhou, Peoples R China.^[Ding, Xiangling] Hunan Key Lab Serv Comp & Novel Software Technol, Xiangtan, Peoples R China.^[Ding, Xiangling] Guangdong Key Lab Informat Secur Technol, Guangzhou, Peoples R China.^[Zhu, Wenjie;Zhang, Dengyong] Changsha Univ Sci & Techno, Sch Comp & Commun Engn, Changsha, Peoples R China.

会议论文集名称： IEEE International Conference on Sensing Communication and Networking

关键词： video forensics;deepfake videos;phase-level stream;temporality-level stream

摘要： While the rapid expansion of DeepFake generation techniques has arisen a serious impact on human society, the detection of DeepFake videos is challenging because of their highly plausible contents on each frame, which are not visually apparent. To address that, this paper proposes a two-stream method to capture the spatial-temporal inconsistency cues, and then interactively fuse them to detect DeepFake videos. Since the traces of spatial inconsistency in DeepFake video frames mainly appear in their structural information, which reflects by the phase component in the frequency domain, the proposed frame-level stream learns the spatial inconsistency from the phase-based reconstructed frames to avoid fitting the content information. Aiming at the problem that the temporal inconsistency in DeepFake videos might be ignored, the temporality-level stream is proposed to extract the temporal correlation feature by the temporal difference networks and stacked ConvGRU module on consecutive multiple frames. When interacted with channel attention in the intermediate layer of two streams, and adaptively fused with the discriminative features of two streams from a global-local perspective, our proposed method performs better than the state-of-the-art detection methods. © 2022 IEEE.

语种： 英文

作者： 朱文杰

作者机构： 长沙理工大学电气与信息工程学院

会议名称： 中国高等学校电力系统及其自动化专业第30届学术年会

会议时间： 20140821

会议地点： 北京

会议论文集名称： 中国高等学校电力系统及其自动化专业第30届学术年会论文集

关键词： 高等院校;《现代电力电子技术与应用》课程;教材编写;内容规划

摘要： 该文从智能电厂、智能电网的教学要求出发确定了电力电子技术写作主题,通过研究对比国内同类书籍(教材)的情况,在一定规划原则下选定了《现代电力电子技术与应用》书籍(教材)规划目录.

语种： 中文