Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection

TL;DR

Diff-ID is an explainable framework that quantifies identity loss to detect DeepFake images, demonstrating high accuracy, robustness to distortions, and superior generalization to unseen manipulations.

Contribution

The paper introduces Diff-ID, a novel method that explains and measures identity loss for DeepFake detection, improving generalization and robustness over existing techniques.

Findings

Achieves high detection accuracy on DeepFake images.

Demonstrates state-of-the-art generalization to unseen forgeries.

Robust against image distortions like compression.

Abstract

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.