On the Generalization of GAN Image Forensics
Xinsheng Xuan,Bo Peng,Wei Wang,Jing Dong +3 more
- 12 Oct 2019
- pp 134-141
TL;DR: Wang et al. as mentioned in this paper proposed to use preprocessed images to train a forensic CNN model, where unstable low level noise cues are destroyed, and the forensics model is forced to learn more intrinsic features to classify the generated and real face images.
read more
Abstract: Recently 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 ensure 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, which is also very challenging. 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 images, unstable low level noise cues are destroyed, and 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.
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
Information Security Threats and Working from Home Culture: Taxonomy, Risk Assessment and Solutions
TL;DR: In this article , the authors present the required taxonomies and perform a thorough analysis of the threats associated with the new work-from-home work culture and present specific use cases.
Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images
Luca Guarnera,Oliver Giudice,Sebastiano Battiato +2 more
- 18 Mar 2022
TL;DR: In this paper , the authors proposed a method to detect how many times a digital image has been processed by a generative architecture for style transfer, and in order to address and study accurately forensic ballistics on deepfake images, some mathematical properties of style transfer operations were investigated.
Detection of AI-Generated Synthetic Faces
TL;DR: In this article , the authors present the most effective techniques proposed in the literature for the detection of synthetic faces and analyze their rationale, present real-world application scenarios, and compare different approaches in terms of accuracy and generalization ability.
Identifying Fake and Real Images by Using Masked Face Periocular Region
Udayasri Nannuri,Kaushik Roy,Jinsheng Xu,Tony Gwyn,Bianca T Govan +4 more
- 24 Jul 2023
TL;DR: A dataset of spoofed masked images generated using the DALL.E 2 tool, performed the ROI extraction using the CNN-DLib detector, and extracted the features using BoVw-sift shows that periocular information can predict whether the masked image is real or fake.
•Posted Content
Fourier Spectrum Discrepancies in Deep Network Generated Images
TL;DR: This paper proposes 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.
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.
Deep Learning Face Attributes in the Wild
Ziwei Liu,Ping Luo,Xiaogang Wang,Xiaoou Tang +3 more
- 07 Dec 2015
TL;DR: A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.
•Posted Content
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TL;DR: This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
6.8K
•Posted Content
Improved Training of Wasserstein GANs
TL;DR: This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.
4.1K
MesoNet: a Compact Facial Video Forgery Detection Network
Darius Afchar,Vincent Nozick,Junichi Yamagishi,Isao Echizen +3 more
- 04 Sep 2018
TL;DR: In this article, a method to automatically and efficiently detect face tampering in videos, and particularly focusing on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face, is presented.
1.1K