Visible to the public Image Feature Detectors for Deepfake Video Detection

TitleImage Feature Detectors for Deepfake Video Detection
Publication TypeConference Paper
Year of Publication2019
AuthorsKharbat, F. F., Elamsy, T., Mahmoud, A., Abdullah, R.
Conference Name2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA)
Date Publishednov
KeywordsBRISK, Classification algorithms, comprehensive test, deep fake video detection, DeepFake, DeepFake Video, Detectors, digital media forensics, false video detection, FAST, FAST algorithms, feature extraction, feature point extraction, feature-detector-descriptors, feature-point detectors, HOG, Human Behavior, human factors, image classification, image feature detectors, Image forensics, Information integrity, KAZE, Metrics, object detection, ORB, pubcrawl, regression analysis, resilience, Resiliency, Scalability, support vector machine regression, Support vector machines, SURF, SVM classifier, SVM regression, Training, video signal processing, Videos
AbstractDetecting DeepFake videos are one of the challenges in digital media forensics. This paper proposes a method to detect deepfake videos using Support Vector Machine (SVM) regression. The SVM classifier can be trained with feature points extracted using one of the different feature-point detectors such as HOG, ORB, BRISK, KAZE, SURF, and FAST algorithms. A comprehensive test of the proposed method is conducted using a dataset of original and fake videos from the literature. Different feature point detectors are tested. The result shows that the proposed method of using feature-detector-descriptors for training the SVM can be effectively used to detect false videos.
Citation Keykharbat_image_2019