Global Texture Enhancement for Fake Face Detection in the Wild

Abstract

Generative Adversarial Networks (GANs) can generate realistic fake face images that can easily fool human beings.On the contrary, a common Convolutional Neural Network(CNN) discriminator can achieve more than 99.9% accuracyin discerning fake/real images. In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets. Motivated by the above observations, we propose a new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection. Experimental results on several datasets demonstrate that our Gram-Net outperforms existing approaches. Especially, our Gram-Netis more robust to image editings, e.g. down-sampling, JPEG compression, blur, and noise. More importantly, our Gram-Net generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detecting fake natural images.

References in corpus (8)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• Identification of Deep Network Generated Images Using Disparities in Color Components
• On Convergence and Stability of GANs
• Detecting GAN generated Fake Images using Co-occurrence Matrices

Cited by in corpus (3)

• Fighting deepfakes by detecting GAN DCT anomalies
• Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
• An Examination of Fairness of AI Models for Deepfake Detection