| Title | Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Matern, F., Riess, C., Stamminger, M. |
| Conference Name | 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW) |
| Keywords | artificial faces, classical computer vision issues, computer animation, Computer vision, DeepFake, Deepfakes, Estimation, Face, face editing algorithms, face manipulations, face recognition, face tracking, Face2Face, facial editing methods, Geometry, high quality face editing, Human Behavior, human factors, lighting, manipulation types, Metrics, pubcrawl, resilience, Resiliency, Scalability, video content, video signal processing, Videos, visual artifacts, visual features, visualization |
| Abstract | High quality face editing in videos is a growing concern and spreads distrust in video content. However, upon closer examination, many face editing algorithms exhibit artifacts that resemble classical computer vision issues that stem from face tracking and editing. As a consequence, we wonder how difficult it is to expose artificial faces from current generators? To this end, we review current facial editing methods and several characteristic artifacts from their processing pipelines. We also show that relatively simple visual artifacts can be already quite effective in exposing such manipulations, including Deepfakes and Face2Face. Since the methods are based on visual features, they are easily explicable also to non-technical experts. The methods are easy to implement and offer capabilities for rapid adjustment to new manipulation types with little data available. Despite their simplicity, the methods are able to achieve AUC values of up to 0.866. |
| DOI | 10.1109/WACVW.2019.00020 |
| Citation Key | matern_exploiting_2019 |
Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations