# Fourier Spectrum Discrepancies in Deep Network Generated Images

arXiv: https://arxiv.org/abs/1911.06465 · HTML: https://mlsanity.com/paper/1911.06465/

## Key facts

- Cited by 139 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 30 of 139)

- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Detecting and Grounding Multi-Modal Media Manipulation](https://mlsanity.com/paper/2304.02556/) (2023)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection](https://mlsanity.com/paper/2103.17195/) (2021)
- [A Bias-Free Training Paradigm for More General AI-generated Image Detection](https://mlsanity.com/paper/2412.17671/) (2024)
- [On the Frequency Bias of Generative Models](https://mlsanity.com/paper/2111.02447/) (2021)
- [Will Large-scale Generative Models Corrupt Future Datasets?](https://mlsanity.com/paper/2211.08095/) (2022)
- [Detecting and Grounding Multi-Modal Media Manipulation and Beyond](https://mlsanity.com/paper/2309.14203/) (2023)
- [A Fourier Space Perspective on Diffusion Models](https://mlsanity.com/paper/2505.11278/) (2025)
- [Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection](https://mlsanity.com/paper/2304.12489/) (2023)
- [Community Forensics: Using Thousands of Generators to Train Fake Image Detectors](https://mlsanity.com/paper/2411.04125/) (2024)
- [Generalizable Synthetic Image Detection via Language-guided Contrastive Learning](https://mlsanity.com/paper/2305.13800/) (2023)
- [ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images](https://mlsanity.com/paper/2112.03553/) (2021)
- [Spectral Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2106.06112/) (2021)
- [RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection](https://mlsanity.com/paper/2405.20112/) (2024)
- [Detecting and Recovering Sequential DeepFake Manipulation](https://mlsanity.com/paper/2207.02204/) (2022)
- [Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?](https://mlsanity.com/paper/2206.14532/) (2022)
- [Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning](https://mlsanity.com/paper/2309.05911/) (2023)
- [Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images](https://mlsanity.com/paper/2304.00500/) (2023)
- [DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection](https://mlsanity.com/paper/2306.00863/) (2023)
- [Wavelet-Packets for Deepfake Image Analysis and Detection](https://mlsanity.com/paper/2106.09369/) (2021)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](https://mlsanity.com/paper/2506.16802/) (2025)
- [Mixture of Low-rank Experts for Transferable AI-Generated Image Detection](https://mlsanity.com/paper/2404.04883/) (2024)
- [Detecting Generated Images by Real Images Only](https://mlsanity.com/paper/2311.00962/) (2023)

## Abstract (arXiv)

Advancements in deep generative models such as generative adversarial networks and variational autoencoders have resulted in the ability to generate realistic images that are visually indistinguishable from real images, which raises concerns about their potential malicious usage. In this paper, we present an analysis of the high-frequency Fourier modes of real and deep network generated images and show that deep network generated images share an observable, systematic shortcoming in replicating the attributes of these high-frequency modes. Using this, we propose a detection method based on the frequency spectrum of the images which is able to achieve an accuracy of up to 99.2% in classifying real and deep network generated images from various GAN and VAE architectures on a dataset of 5000 images with as few as 8 training examples. Furthermore, we show the impact of image transformations such as compression, cropping, and resolution reduction on the classification accuracy and suggest a method for modifying the high-frequency attributes of deep network generated images to mimic real images.