DeepFake Detection with Inconsistent Head Poses: Reproducibility and Analysis
This work corrects misconceptions in DeepFake detection literature, addressing security and media integrity concerns, but is incremental as it focuses on reproducibility and analysis of an existing method.
The paper tackled the problem of DeepFake detection by analyzing an existing head pose estimation method, finding that its effectiveness is dramatically overstated, and uncovered generalizable insights into facial landmark detection and algorithmic bias.
Applications of deep learning to synthetic media generation allow the creation of convincing forgeries, called DeepFakes, with limited technical expertise. DeepFake detection is an increasingly active research area. In this paper, we analyze an existing DeepFake detection technique based on head pose estimation, which can be applied when fake images are generated with an autoencoder-based face swap. Existing literature suggests that this method is an effective DeepFake detector, and its motivating principles are attractively simple. With an eye towards using these principles to develop new DeepFake detectors, we conduct a reproducibility study of the existing method. We conclude that its merits are dramatically overstated, despite its celebrated status. By investigating this discrepancy we uncover a number of important and generalizable insights related to facial landmark detection, identity-agnostic head pose estimation, and algorithmic bias in DeepFake detectors. Our results correct the current literature's perception of state of the art performance for DeepFake detection.