Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection

Digital beautification through social media filters has become increasingly popular, raising concerns about the reliability of facial images and videos and the effectiveness of automated face analysis. This issue is particularly critical for digital manipulation detectors, systems aiming at distinguishing between genuine and manipulated data, especially in cases involving deepfakes and morphing attacks designed to deceive humans and automated facial recognition. This study examines whether beauty filters impact the performance of deepfake and morphing attack detectors. We perform a comprehensive analysis, evaluating multiple state-of-the-art detectors on benchmark datasets before and after applying various smoothing filters. Our findings reveal performance degradation, highlighting vulnerabilities introduced by facial enhancements and underscoring the need for robust detection models resilient to such alterations.

Key Contributions

Comprehensive evaluation of multiple state-of-the-art deepfake and morphing attack detectors before and after application of smoothing/beauty filters at varying intensity levels
Analysis of how increasing levels of facial beautification (parameterized by smoothing radius as a fraction of face height) progressively degrade detector performance
Separate evaluation of filter effects on bona fide vs. manipulated images, distinguishing naive beauty use from adversarial evasion of detectors

🛡️ Threat Analysis

Output Integrity Attack

The paper's primary subject is the robustness of deepfake and morphing attack detectors — AI-generated content detection systems — under beauty filter transformations. Performance degradation in these detectors directly undermines output integrity and content authenticity verification, core concerns of ML09.