Global Texture Enhancement for Fake Face Detection in the Wild

By Zhengzhe Liu, Xiaojuan Qi, Jiaya Jia, Philip H. S. Torr. Computer Vision and Pattern Recognition, 2020

450 citations recorded by the source corpus.

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 than99.9%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-Netoutperforms existing approaches. Especially, our Gram-Netis more robust to image editings, e.g. down-sampling, JPEGcompression, 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

View Paper: https://www.semanticscholar.org/paper/985c4c6b6dd50ebb9871792d5e8d47a5161f87de

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yunhe Wang
2. Yunchao Wei
3. Shikui Wei
4. Yao Zhao
5. Ning Yu
6. Hanting Chen
7. Luisa Verdoliva
8. Chuangchuang Tan

Citations in the corpus

• GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image (2023, methodology): “GramNet [27] uses global texture features to make fake face detection more robust and generalizable.”
• Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection (2023, background): “Some studies [16, 30, 45] focus on human face images, while others [11,18,19,42] handle various categories of images.”
• Generalizing Face Forgery Detection with High-frequency Features (2021, background): “[29, 34, 55, 9, 7, 32] targeted at specific artifacts such as abnormal eye-blinking frequency [29] or head-pose inconsistency [55].”
• Detecting CNN-Generated Facial Images in Real-World Scenarios (2020, methodology): “Lastly, [27] examines human performance of detecting GAN-generated images as a direct comparison with algorithmic detection.”
• Media Forensics and DeepFakes: An Overview (2020, background): “a CNN that incorporates global image texture information in different semantic levels [186].”
• Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data (2020, background): “[56, 13, 12] point out that the high-frequency pattern mismatch can be used for deepfake detection, so can the texture feature mismatch [32].”
• Local Relation Learning for Face Forgery Detection (2021, unknown): “…a novel perspective of face forgery detection via local relation learning to focuses on the relation of local regions, which is a generalized descriptor that can be used to effectively capture the forged trace, such as abnormal texture (Liu et al. 2020) and high frequency noise (Qian et al. 2020).”