합성곱신경망 기반의 StyleGAN 이미지 탐지모델 = A StyleGAN Image Detection Model Based on Convolutional Neural Network

다국어 초록 (Multilingual Abstract)

As artificial intelligence technology is actively used in image processing, it is possible to generate high-quality fake images based on deep learning. Fake images generated using GAN(Generative Adversarial Network), one of unsupervised learning algorithms, have reached levels that are hard to discriminate from the naked eye. Detecting these fake images is required as they can be abused for crimes such as illegal content production, identity fraud and defamation. In this paper, we develop a deep-learning model based on CNN(Convolutional Neural Network) for the detection of StyleGAN fake images. StyleGAN is one of GAN algorithms and has an excellent performance in generating face images. We experiment with 48 number of experimental scenarios developed by combining parameters of the proposed model. We train and test each scenario with 300,000 number of real and fake face images in order to present a model parameter that improves performance in the detection of fake faces.

참고문헌 (Reference)

1 김대희, "딥 러닝 기반의 가짜 얼굴 검출" 한국산업정보학회 23 (23): 9-17, 2018

2 A. Radford, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks" 2015

3 J. Y. Zhu, "Unpaired Image-to-image Translation Using Cycle-consistent Adversarial Networks" 2223-2232, 2017

4 Yang Yang, "TI-CNN:Convolutional Neural Networks for Fake News Detection"

5 Y. J. Choi, "Stargan : Unified Generative Adversarial Networks for Multi-domain Image-to-image Translation" 8789-8797, 2018

6 S. K. Yarlagadda, "Satellite Image Forgery Detection and Localization Using GAN and One-class Classifier" 7 : 1-9, 2018

7 류세열, "ResNet을 이용한 얼굴 인식 기반 출입관리시스템 개발" 한국멀티미디어학회 22 (22): 823-831, 2019

8 T. Karras, "Progressive Growing of Gans for Improved Quality, Stability, and Variation" 2017

9 X. Xuan, "On the Generalization of GAN Image Forensics" Springer 134-141, 2019

10 C. C. Hsu, "Learning to Detect Fake Face Images in the Wild" 388-391, 2018

11 I. J. Goodfellow, "Generative Adversarial Nets" 2672-2680, 2014

12 S. Tariq, "GAN Is a Friend or Foe? : a Framework to Detect Various Fake Face Images" 1296-1303, 2019

13 T.D. Nhu, "Forensics Face Detection From GANs Using Convolutional Neural Network" 2018

14 H. Li, "Detection of Deep Network Generated Images Using Disparities in Color Components" 2018

15 X. Zhang, "Detecting and Simulating Artifacts in GAN Fake Images" 2019

16 L. Nataraj, "Detecting GAN Generated Fake Images Using Co-occurrence Matrices" 2019

17 L. Dang, "Deep Learning Based Computer Generated Face Identification Using Convolutional Neural Network" MDPI AG 8 (8): 2610-, 2018

18 C. C. Hsu, "Deep Fake Image Detection Based on Pairwise Learning" 2019

19 D. Berthelot, "Began: Boundary Equilibrium Generative Adversarial Networks" 2017

20 T. Karras, "A Stylebased Generator Architecture for Generative Adversarial Networks" 4401-4410, 2019