| Title | Effective and Fast DeepFake Detection Method Based on Haar Wavelet Transform |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Younus, M. A., Hasan, T. M. |
| Conference Name | 2020 International Conference on Computer Science and Software Engineering (CSASE) |
| Keywords | Blur inconsistency, blur inconsistency detection scheme, DeepFake, DeepFake detection method, DeepFake generation algorithms, DeepFake videos, detection rate, distortion, exclusive blur inconsistency, Face, face images, face recognition, face region, fake face, feature extraction, Gallium nitride, gan, generated face, generative adversarial networks, Generative Adversarial Networks GANs, Haar transforms, Haar wavelet, Haar wavelet transform, high-quality fake videos, Human Behavior, human factors, Image edge detection, Metrics, neural nets, object detection, pubcrawl, realistic manner, resilience, Resiliency, Scalability, source video, surrounding context, video signal processing, Videos, Wavelet domain, wavelet transforms |
| Abstract | DeepFake using Generative Adversarial Networks (GANs) tampered videos reveals a new challenge in today's life. With the inception of GANs, generating high-quality fake videos becomes much easier and in a very realistic manner. Therefore, the development of efficient tools that can automatically detect these fake videos is of paramount importance. The proposed DeepFake detection method takes the advantage of the fact that current DeepFake generation algorithms cannot generate face images with varied resolutions, it is only able to generate new faces with a limited size and resolution, a further distortion and blur is needed to match and fit the fake face with the background and surrounding context in the source video. This transformation causes exclusive blur inconsistency between the generated face and its background in the outcome DeepFake videos, in turn, these artifacts can be effectively spotted by examining the edge pixels in the wavelet domain of the faces in each frame compared to the rest of the frame. A blur inconsistency detection scheme relied on the type of edge and the analysis of its sharpness using Haar wavelet transform as shown in this paper, by using this feature, it can determine if the face region in a video has been blurred or not and to what extent it has been blurred. Thus will lead to the detection of DeepFake videos. The effectiveness of the proposed scheme is demonstrated in the experimental results where the "UADFV" dataset has been used for the evaluation, a very successful detection rate with more than 90.5% was gained. |
| DOI | 10.1109/CSASE48920.2020.9142077 |
| Citation Key | younus_effective_2020 |
Effective and Fast DeepFake Detection Method Based on Haar Wavelet Transform