Deepfake detection of occluded images using a patch-based approach

DeepFake involves the use of deep learning and artificial intelligence techniques to produce or change video and image contents typically generated by GANs. Moreover, it can be misused and leads to fictitious news, ethical and financial crimes, and also affects the performance of facial recognition systems. Thus, detection of real or fake images is significant specially to authenticate originality of people's images or videos. One of the most important challenges in this topic is obstruction that decreases the system precision. In this study, we present a deep learning approach using the entire face and face patches to distinguish real/fake images in the presence of limitations of blurring, compression, scaling and especially obstruction with a three-path decision: first entire-face reasoning, second a decision based on the concatenation of feature vectors of face patches, and third a majority vote decision based on these features. To test our approach, new data sets including real and fake images are created. For producing fake images, StyleGAN and StyleGAN2 are trained by FFHQ images and also StarGAN and PGGAN are trained by CelebA images. The CelebA and FFHQ data sets are used as real images. The proposed approach reaches higher results in early epochs than other methods and increases the SoTA results by 0.4%-7.9% in the different built data sets. In addition, we have shown in experimental results that weighing the patches may improve accuracy.

Automated summary

DeepFake involves the use of deep learning and artificial intelligence techniques to produce or change video and image contents. It can lead to fake news, crimes, and affect facial recognition systems. This study presents a deep learning approach using the entire face and face patches to distinguish real/fake images, overcoming limitations like blurring and obstruction. Experimental results show that this approach performs better and weighing the patches improves accuracy.