{"title":"Deep Fakes的心脏是如何跳动的?基于生物信号残差解释的深度假源检测","authors":"U. Ciftci, Ilke Demir, L. Yin","doi":"10.1109/IJCB48548.2020.9304909","DOIUrl":null,"url":null,"abstract":"Fake portrait video generation techniques have been posing a new threat to the society with photorealistic deep fakes for political propaganda, celebrity imitation, forged evidences, and other identity related manipulations. Following these generation techniques, some detection approaches have also been proved useful due to their high classification accuracy. Nevertheless, almost no effort was spent to track down the source of deep fakes. We propose an approach not only to separate deep fakes from real videos, but also to discover the specific generative model behind a deep fake. Some pure deep learning based approaches try to classify deep fakes using CNNs where they actually learn the residuals of the generator. We believe that these residuals contain more information and we can reveal these manipulation artifacts by disentangling them with biological signals. Our key observation yields that the spatiotemporal patterns in biological signals can be conceived as a representative projection of residuals. To justify this observation, we extract PPG cells from real and fake videos and feed these to a state-of-the-art classification network for detecting the generative model per video. Our results indicate that our approach can detect fake videos with 97.29% accuracy, and the source model with 93.39% accuracy.","PeriodicalId":417270,"journal":{"name":"2020 IEEE International Joint Conference on Biometrics (IJCB)","volume":"13 2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"48","resultStr":"{\"title\":\"How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signals\",\"authors\":\"U. Ciftci, Ilke Demir, L. Yin\",\"doi\":\"10.1109/IJCB48548.2020.9304909\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Fake portrait video generation techniques have been posing a new threat to the society with photorealistic deep fakes for political propaganda, celebrity imitation, forged evidences, and other identity related manipulations. Following these generation techniques, some detection approaches have also been proved useful due to their high classification accuracy. Nevertheless, almost no effort was spent to track down the source of deep fakes. We propose an approach not only to separate deep fakes from real videos, but also to discover the specific generative model behind a deep fake. Some pure deep learning based approaches try to classify deep fakes using CNNs where they actually learn the residuals of the generator. We believe that these residuals contain more information and we can reveal these manipulation artifacts by disentangling them with biological signals. Our key observation yields that the spatiotemporal patterns in biological signals can be conceived as a representative projection of residuals. To justify this observation, we extract PPG cells from real and fake videos and feed these to a state-of-the-art classification network for detecting the generative model per video. Our results indicate that our approach can detect fake videos with 97.29% accuracy, and the source model with 93.39% accuracy.\",\"PeriodicalId\":417270,\"journal\":{\"name\":\"2020 IEEE International Joint Conference on Biometrics (IJCB)\",\"volume\":\"13 2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-08-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"48\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Joint Conference on Biometrics (IJCB)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IJCB48548.2020.9304909\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Joint Conference on Biometrics (IJCB)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IJCB48548.2020.9304909","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signals
Fake portrait video generation techniques have been posing a new threat to the society with photorealistic deep fakes for political propaganda, celebrity imitation, forged evidences, and other identity related manipulations. Following these generation techniques, some detection approaches have also been proved useful due to their high classification accuracy. Nevertheless, almost no effort was spent to track down the source of deep fakes. We propose an approach not only to separate deep fakes from real videos, but also to discover the specific generative model behind a deep fake. Some pure deep learning based approaches try to classify deep fakes using CNNs where they actually learn the residuals of the generator. We believe that these residuals contain more information and we can reveal these manipulation artifacts by disentangling them with biological signals. Our key observation yields that the spatiotemporal patterns in biological signals can be conceived as a representative projection of residuals. To justify this observation, we extract PPG cells from real and fake videos and feed these to a state-of-the-art classification network for detecting the generative model per video. Our results indicate that our approach can detect fake videos with 97.29% accuracy, and the source model with 93.39% accuracy.