Through the Lens: Benchmarking Deepfake Detectors Against Moir\'e-Induced Distortions

TL;DR

This paper evaluates how Moiré artifacts from real-world smartphone-captured videos impact deepfake detection, revealing significant performance degradation and highlighting the need for more robust detection methods.

Contribution

It introduces the DMF dataset and systematically assesses the effect of Moiré distortions on state-of-the-art deepfake detectors, exposing vulnerabilities and challenging existing mitigation strategies.

Findings

Moiré artifacts reduce detection accuracy by up to 25.4%.

Synthetic Moiré patterns cause a 21.4% accuracy drop.

Demoiré techniques can worsen detection performance by up to 17.2%.

Abstract

Deepfake detection remains a pressing challenge, particularly in real-world settings where smartphone-captured media from digital screens often introduces Moir\'e artifacts that can distort detection outcomes. This study systematically evaluates state-of-the-art (SOTA) deepfake detectors on Moir\'e-affected videos, an issue that has received little attention. We collected a dataset of 12,832 videos, spanning 35.64 hours, from the Celeb-DF, DFD, DFDC, UADFV, and FF++ datasets, capturing footage under diverse real-world conditions, including varying screens, smartphones, lighting setups, and camera angles. To further examine the influence of Moir\'e patterns on deepfake detection, we conducted additional experiments using our DeepMoir\'eFake, referred to as (DMF) dataset and two synthetic Moir\'e generation techniques. Across 15 top-performing detectors, our results show that Moir\'e artifacts degrade performance by as much as 25.4%, while synthetically generated Moir\'e patterns lead to a 21.4% drop in accuracy. Surprisingly, demoir\'eing methods, intended as a mitigation approach, instead worsened the problem, reducing accuracy by up to 17.2%. These findings underscore the urgent need for detection models that can robustly handle Moir\'e distortions alongside other realworld challenges, such as compression, sharpening, and blurring. By introducing the DMF dataset, we aim to drive future research toward closing the gap between controlled experiments and practical deepfake detection.