Detecting and Simulating Artifacts in GAN Fake Images
Xu Zhang,Svebor Karaman,Shih-Fu Chang +2 more
- 15 Jul 2019
- pp 1-6
TL;DR: A GAN simulator, AutoGAN, is proposed, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models, and identifies a unique artifact caused by the up-sampling component included in the common GAN pipelines.
read more
Abstract: To detect GAN generated images, conventional supervised machine learning algorithms require collecting a large number of real images as well as fake images generated by 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 pipelines. 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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Manipulated Face Detector: Joint Spatial and Frequency Domain Attention Network
Zehao Chen,Hua Yang +1 more
- 06 May 2020
TL;DR: A novel manipulated face detector, which is based on spatial and frequency domain combination and attention mechanism, and adds attention-based layers to backbone networks, in order to improve its generalization ability.
REVEAL: A Retrieval-Augmented Generation Approach for Contextual Identification of Synthetic Visual Content
Mamadou Keita,Wassim Hamidouche,Abdelmailk Taleb-Ahmed,Abdenour Hadid +3 more
- 08 Oct 2025
TL;DR: Researchers propose REVEAL, a retrieval-augmented generation approach for detecting AI-generated images, achieving 93.90% accuracy on 19 generative models and 80.29% under degraded conditions, outperforming existing methods with strong generalization and robustness.
•Posted Content
DeepTag: Robust Image Tagging for DeepFake Provenance
TL;DR: A deep learning-based approach with a simple yet effective encoder and decoder design to embed message to the facial image, which is to recover the embedded message after various drastic GAN-based DeepFake transformation with high confidence.
Blockwise Spectral Analysis for Deepfake Detection in High-fidelity Videos
TL;DR: In this article , the spectral artifacts left by up-sampling operations are exploited for detecting high-fidelity deepfake videos, e.g., face, eyes, and mouth areas.
Towards Better Morphed Face Images without Ghosting Artifacts
TL;DR: The proposed method for automatic prevention of ghosting artifacts based on a pixel-wise alignment during morph generation is evaluated on state-of-the-art detectors and shows that its morphs are harder to detect, particularly, when combined with style-transfer-based improvement of low-level image characteristics.
References
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
- 08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Image-to-Image Translation with Conditional Adversarial Networks
Phillip Isola,Jun-Yan Zhu,Tinghui Zhou,Alexei A. Efros +3 more
- 21 Jul 2017
TL;DR: Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
Jun-Yan Zhu,Taesung Park,Phillip Isola,Alexei A. Efros +3 more
- 01 Oct 2017
TL;DR: CycleGAN as discussed by the authors learns a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss.
19.5K
•Posted Content
Image-to-Image Translation with Conditional Adversarial Networks
TL;DR: Conditional Adversarial Network (CA) as discussed by the authors is a general-purpose solution to image-to-image translation problems, which can be used to synthesize photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
15.5K