Various deepfake detectors have been proposed, but challenges still exist to detect images of unknown categories or GAN models outside of the training settings. Such issues arise from the overfitting issue, which we discover from our own analysis and the previous studies to originate from the frequency-level artifacts in generated images. We find that ignoring the frequency-level artifacts can improve the detector's generalization across various GAN models, but it can reduce the model's performance for the trained GAN models. Thus, we design a framework to generalize the deepfake detector for both the known and unseen GAN models. Our framework generates the frequency-level perturbation maps to make the generated images indistinguishable from the real images. By updating the deepfake detector along with the training of the perturbation generator, our model is trained to detect the frequency-level artifacts at the initial iterations and consider the image-level irregularities at the last iterations. For experiments, we design new test scenarios varying from the training settings in GAN models, color manipulations, and object categories. Numerous experiments validate the state-of-the-art performance of our deepfake detector.
翻译:提出了各种深假探测器,但是在检测培训环境之外未知类别或GAN模型的图像方面仍然存在挑战。这些问题产生于超称问题,我们从自己的分析和先前的研究中发现,这些问题源于生成图像中的频率级文物。我们发现,忽略频率级文物可以改进各种GAN模型中的探测器的概观,但可以减少经过培训的GAN模型的模型性能。因此,我们设计了一个框架,用于对已知和看不见的GAN模型的深假探测器进行普及。我们的框架生成频率级扰动图,使生成的图像与真实图像无法区分。通过更新深假探测器,加上对扰动生成器的培训,我们的模型经过培训,可以在最初的图像中检测频率级文物,并在最后的迭代中考虑图像级异常。在实验中,我们设计了不同于GAN模型的培训环境、彩色操纵和对象类别的新测试情景。许多实验都验证了我们深度探测器的状态性能。