Exploring the Impact of Moire Pattern on Deepfake Detectors

TL;DR

This paper investigates how Moiré patterns, caused by camera capture of digital screens, significantly impair the accuracy of deepfake detectors, highlighting a critical challenge for real-world applications.

Contribution

It is the first study to systematically analyze the impact of Moiré patterns on deepfake detection performance using real-world camera-captured videos.

Findings

Detector accuracy drops below 68% with Moiré patterns

Moiré patterns significantly confound deepfake classifiers

Current detectors are vulnerable to camera-induced artifacts

Abstract

Deepfake detection is critical in mitigating the societal threats posed by manipulated videos. While various algorithms have been developed for this purpose, challenges arise when detectors operate externally, such as on smartphones, when users take a photo of deepfake images and upload on the Internet. One significant challenge in such scenarios is the presence of Moir\'e patterns, which degrade image quality and confound conventional classification algorithms, including deep neural networks (DNNs). The impact of Moir\'e patterns remains largely unexplored for deepfake detectors. In this study, we investigate how camera-captured deepfake videos from digital screens affect detector performance. We conducted experiments using two prominent datasets, CelebDF and FF++, comparing the performance of four state-of-the-art detectors on camera-captured deepfake videos with introduced Moir\'e patterns. Our findings reveal a significant decline in detector accuracy, with none achieving above 68% on average. This underscores the critical need to address Moir\'e pattern challenges in real-world deepfake detection scenarios.