Leveraging Frequency Analysis for Deep Fake Image Recognition

Abstract

Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While deep fake images have been thoroughly investigated in the image domain - a classical approach from the area of image forensics - an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.

Accepted to ICML 2020. New experiments, updated several sections, code: https://github.com/RUB-SysSec/GANDCTAnalysis

References in corpus (13)

• Conditional Generative Adversarial Nets
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Neural Discrete Representation Learning
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• Making Convolutional Networks Shift-Invariant Again
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Why do deep convolutional networks generalize so poorly to small image transformations?
• On the regularization of Wasserstein GANs
• Detecting GAN-generated Imagery using Color Cues
• Everybody's Talkin': Let Me Talk as You Want
• TequilaGAN: How to easily identify GAN samples

Cited by in corpus (24)

• A Review of Deep Learning-based Approaches for Deepfake Content Detection
• Wavelet-Packets for Deepfake Image Analysis and Detection
• Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
• Identifying and Mitigating the Security Risks of Generative AI
• Copyright Protection and Accountability of Generative AI:Attack, Watermarking and Attribution
• FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects
• DeFakePro: Decentralized DeepFake Attacks Detection using ENF Authentication
• Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective
• FaceGuard: Proactive Deepfake Detection
• SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
• Detection, Attribution and Localization of GAN Generated Images
• FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
• Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
• Language-Driven Image Style Transfer
• Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
• FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
• Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
• Automated Deepfake Detection
• Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
• F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
• [RE] CNN-generated images are surprisingly easy to spot...for now
• Generalized Spoofing Detection Inspired from Audio Generation Artifacts
• Modeling the Nonsmoothness of Modern Neural Networks
• On the Frequency Bias of Generative Models