Fake Visual Content Detection Using Two-Stream Convolutional Neural Networks

TL;DR

This paper introduces a two-stream CNN approach that combines frequency and spatial features to improve the detection and generalization of fake visual content across different datasets and generation methods.

Contribution

The paper proposes a novel two-stream CNN architecture, TwoStreamNet, that leverages frequency and spatial domain features to enhance fake visual content detection and generalization.

Findings

Significant performance improvement over state-of-the-art detectors.

Enhanced generalization to unseen generation architectures and datasets.

Fusing frequency and spatial streams improves detection accuracy.

Abstract

Rapid progress in adversarial learning has enabled the generation of realistic-looking fake visual content. To distinguish between fake and real visual content, several detection techniques have been proposed. The performance of most of these techniques however drops off significantly if the test and the training data are sampled from different distributions. This motivates efforts towards improving the generalization of fake detectors. Since current fake content generation techniques do not accurately model the frequency spectrum of the natural images, we observe that the frequency spectrum of the fake visual data contains discriminative characteristics that can be used to detect fake content. We also observe that the information captured in the frequency spectrum is different from that of the spatial domain. Using these insights, we propose to complement frequency and spatial domain features using a two-stream convolutional neural network architecture called TwoStreamNet. We demonstrate the improved generalization of the proposed two-stream network to several unseen generation architectures, datasets, and techniques. The proposed detector has demonstrated significant performance improvement compared to the current state-of-the-art fake content detectors and fusing the frequency and spatial domain streams has also improved generalization of the detector.