Deepfake Representation with Multilinear Regression
This addresses the need for discrimination techniques against deepfakes, which can cause social, political, or economic upheaval, but the approach appears incremental.
The paper tackled the problem of detecting deepfake media by proposing a modified multilinear (tensor) regression method for representation, achieving encouraging results in SVM classification.
Generative neural network architectures such as GANs, may be used to generate synthetic instances to compensate for the lack of real data. However, they may be employed to create media that may cause social, political or economical upheaval. One emerging media is "Deepfake".Techniques that can discriminate between such media is indispensable. In this paper, we propose a modified multilinear (tensor) method, a combination of linear and multilinear regressions for representing fake and real data. We test our approach by representing Deepfakes with our modified multilinear (tensor) approach and perform SVM classification with encouraging results.