Deepfake Representation with Multilinear Regression

TL;DR

This paper introduces a modified multilinear tensor method to distinguish Deepfake media from real data, combining linear and multilinear regressions, and demonstrates its effectiveness through SVM classification.

Contribution

It presents a novel multilinear tensor approach for Deepfake detection, integrating linear and multilinear regressions for improved media representation.

Findings

Encouraging classification results with SVM.

Effective representation of Deepfakes using the proposed method.

Potential for improved Deepfake detection accuracy.

Abstract

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.