Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
This addresses the need for reliable detection of fake images to prevent malicious uses like deepfakes, representing an incremental improvement over existing methods.
The paper tackles the problem of detecting GAN-generated images, which is crucial for combating deepfakes, by proposing a robust detection framework based on multi-view image completion representation. The results show improved effectiveness, generalization, and robustness across six GANs and various perturbation attacks compared to baselines.
GAN-generated image detection now becomes the first line of defense against the malicious uses of machine-synthesized image manipulations such as deepfakes. Although some existing detectors work well in detecting clean, known GAN samples, their success is largely attributable to overfitting unstable features such as frequency artifacts, which will cause failures when facing unknown GANs or perturbation attacks. To overcome the issue, we propose a robust detection framework based on a novel multi-view image completion representation. The framework first learns various view-to-image tasks to model the diverse distributions of genuine images. Frequency-irrelevant features can be represented from the distributional discrepancies characterized by the completion models, which are stable, generalized, and robust for detecting unknown fake patterns. Then, a multi-view classification is devised with elaborated intra- and inter-view learning strategies to enhance view-specific feature representation and cross-view feature aggregation, respectively. We evaluated the generalization ability of our framework across six popular GANs at different resolutions and its robustness against a broad range of perturbation attacks. The results confirm our method's improved effectiveness, generalization, and robustness over various baselines.