# On the generalization of GAN image forensics

arXiv: https://arxiv.org/abs/1902.11153 · HTML: https://mlsanity.com/paper/1902.11153/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2019.

## Built on by (most cited first, 30 of 36)

- [Detecting Deepfakes with Self-Blended Images](https://mlsanity.com/paper/2204.08376/) (2022)
- [Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain](https://mlsanity.com/paper/2103.01856/) (2021)
- [Exploring Temporal Coherence for More General Video Face Forgery Detection](https://mlsanity.com/paper/2108.06693/) (2021)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization](https://mlsanity.com/paper/2210.14457/) (2022)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Predicting Video with VQVAE](https://mlsanity.com/paper/2103.01950/) (2021)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Perceptual Artifacts Localization for Image Synthesis Tasks](https://mlsanity.com/paper/2310.05590/) (2023)
- [Video Transformer for Deepfake Detection with Incremental Learning](https://mlsanity.com/paper/2108.05307/) (2021)
- [Towards Universal GAN Image Detection](https://mlsanity.com/paper/2112.12606/) (2021)
- [The Age of Synthetic Realities: Challenges and Opportunities](https://mlsanity.com/paper/2306.11503/) (2023)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [Metric Learning for Anti-Compression Facial Forgery Detection](https://mlsanity.com/paper/2103.08397/) (2021)
- [Deepfake detection by exploiting surface anomalies: the SurFake approach](https://mlsanity.com/paper/2310.20621/) (2023)
- [Hybrid Transformer Network for Deepfake Detection](https://mlsanity.com/paper/2208.05820/) (2022)
- [Adversarially robust deepfake media detection using fused convolutional neural network predictions](https://mlsanity.com/paper/2102.05950/) (2021)
- [Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images](https://mlsanity.com/paper/2203.09928/) (2022)
- [Assessment Framework for Deepfake Detection in Real-world Situations](https://mlsanity.com/paper/2304.06125/) (2023)
- [Deep Insights of Deepfake Technology : A Review](https://mlsanity.com/paper/2105.00192/) (2021)
- [Dataset and Case Studies for Visual Near-Duplicates Detection in the Context of Social Media](https://mlsanity.com/paper/2203.07167/) (2022)
- [Impact of Video Processing Operations in Deepfake Detection](https://mlsanity.com/paper/2303.17247/) (2023)
- [Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection](https://mlsanity.com/paper/2307.11438/) (2023)
- [FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended Images](https://mlsanity.com/paper/2406.08625/) (2024)
- [Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detector](https://mlsanity.com/paper/2408.16892/) (2024)
- [CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attention](https://mlsanity.com/paper/2505.18035/) (2025)
- [Fake Visual Content Detection Using Two-Stream Convolutional Neural Networks](https://mlsanity.com/paper/2101.00676/) (2021)
- [Adaptive Frequency Learning in Two-branch Face Forgery Detection](https://mlsanity.com/paper/2203.14315/) (2022)
- [DF-Captcha: A Deepfake Captcha for Preventing Fake Calls](https://mlsanity.com/paper/2208.08524/) (2022)
- [Spritz-PS: Validation of Synthetic Face Images Using a Large Dataset of Printed Documents](https://mlsanity.com/paper/2304.02982/) (2023)

## Abstract (arXiv)

Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the forensics community keeps on developing methods to detect these generated fake images and try to guarantee the credibility of visual contents. Although researchers have developed some methods to detect generated images, few of them explore the important problem of generalization ability of forensics model. As new types of GANs are emerging fast, the generalization ability of forensics models to detect new types of GAN images is absolutely an essential research topic. In this paper, we explore this problem and propose to use preprocessed images to train a forensic CNN model. By applying similar image level preprocessing to both real and fake training images, the forensics model is forced to learn more intrinsic features to classify the generated and real face images. Our experimental results also prove the effectiveness of the proposed method.