Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection
This addresses the need for more robust and generalizable DeepFake detection methods, which is crucial for security and media integrity, though it appears incremental as it builds on existing face-swapping and identity feature techniques.
The authors tackled the problem of DeepFake detection generalizing poorly to unseen manipulations and being fragile to image distortions by proposing Diff-ID, a framework that quantifies identity loss using a reference image and face-swapping alignment, achieving high detection performance and state-of-the-art generalization ability.
Despite the fact that DeepFake forgery detection algorithms have achieved impressive performance on known manipulations, they often face disastrous performance degradation when generalized to an unseen manipulation. Some recent works show improvement in generalization but rely on features fragile to image distortions such as compression. To this end, we propose Diff-ID, a concise and effective approach that explains and measures the identity loss induced by facial manipulations. When testing on an image of a specific person, Diff-ID utilizes an authentic image of that person as a reference and aligns them to the same identity-insensitive attribute feature space by applying a face-swapping generator. We then visualize the identity loss between the test and the reference image from the image differences of the aligned pairs, and design a custom metric to quantify the identity loss. The metric is then proved to be effective in distinguishing the forgery images from the real ones. Extensive experiments show that our approach achieves high detection performance on DeepFake images and state-of-the-art generalization ability to unknown forgery methods, while also being robust to image distortions.