Detecting and Simulating Artifacts in GAN Fake Images

Abstract

To detect GAN generated images, conventional supervised machine learning algorithms require collection of a number of real and fake images from the targeted GAN model. However, the specific model used by the attacker is often unavailable. To address this, we propose a GAN simulator, AutoGAN, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models. Additionally, we identify a unique artifact caused by the up-sampling component included in the common GAN pipeline. We show theoretically such artifacts are manifested as replications of spectra in the frequency domain and thus propose a classifier model based on the spectrum input, rather than the pixel input. By using the simulated images to train a spectrum based classifier, even without seeing the fake images produced by the targeted GAN model during training, our approach achieves state-of-the-art performances on detecting fake images generated by popular GAN models such as CycleGAN.

This is an extended version of our original AutoGAN paper which will be appeared in WIFS 2019

References in corpus (7)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
• Detecting GAN-generated Imagery using Color Cues
• Detecting GAN generated Fake Images using Co-occurrence Matrices
• Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
• Source Generator Attribution via Inversion

Cited by in corpus (11)

• Media Forensics and DeepFakes: an overview
• Fighting deepfakes by detecting GAN DCT anomalies
• Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues
• FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
• GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
• SoK: Machine Learning Governance
• Decentralized Attribution of Generative Models
• Adversarial Attacks on Co-Occurrence Features for GAN Detection
• Combating Disinformation in a Social Media Age
• Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
• Exploring constraints on CycleGAN-based CBCT enhancement for adaptive radiotherapy