دورية أكاديمية

DeepRhythm: Exposing deepfakes with attentional visual heartbeat rhythms

التفاصيل البيبلوغرافية
العنوان: DeepRhythm: Exposing deepfakes with attentional visual heartbeat rhythms
المؤلفون: QI, Hua, GUO, Qing, JUEFEI-XU, Felix, XIE, Xiaofei, MA, Lei, FENG, Wei, LIU, Yang, ZHAO, Jianjun
المصدر: Research Collection School Of Computing and Information Systems
بيانات النشر: Institutional Knowledge at Singapore Management University
سنة النشر: 2020
المجموعة: Institutional Knowledge (InK) at Singapore Management University
مصطلحات موضوعية: DeepFake detection, heartbeat rhythm, remote photoplethysmography (PPG), dual-spatial-temporal attention, face forensics, Graphics and Human Computer Interfaces, Software Engineering
الوصف: As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors. Motivated by the fact that remote visual photoplethysmography (PPG) is made possible by monitoring the minuscule periodic changes of skin color due to blood pumping through the face, we conjecture that normal heartbeat rhythms found in the real face videos will be disrupted or even entirely broken in a DeepFake video, making it a potentially powerful indicator for DeepFake detection. In this work, we propose DeepRhythm, a DeepFake detection technique that exposes DeepFakes by monitoring the heartbeat rhythms. DeepRhythm utilizes dual-spatial-temporal attention to adapt to dynamically changing face and fake types. Extensive experiments on FaceForensics++ and DFDC-preview datasets have confirmed our conjecture and demonstrated not only the effectiveness, but also the generalization capability of DeepRhythm over different datasets by various DeepFakes generation techniques and multifarious challenging degradations.
نوع الوثيقة: text
وصف الملف: application/pdf
اللغة: English
العلاقة: https://ink.library.smu.edu.sg/sis_research/7079Test; https://ink.library.smu.edu.sg/context/sis_research/article/8082/viewcontent/3394171.3413707.pdfTest
DOI: 10.1145/3394171.3413707
الإتاحة: https://doi.org/10.1145/3394171.3413707Test
https://ink.library.smu.edu.sg/sis_research/7079Test
https://ink.library.smu.edu.sg/context/sis_research/article/8082/viewcontent/3394171.3413707.pdfTest
حقوق: http://creativecommons.org/licenses/by-nc-nd/4.0Test/
رقم الانضمام: edsbas.C69AF467
قاعدة البيانات: BASE