Abstract
In recent times, image synthesis has attracted significant attention of people for both positive and negative reasons. Images can be easily synthesized using various techniques. This paper surveys various techniques for image synthesis as well as its detection in a unique structured manner, to enable a perspective on this iterative phenomenon. The paper describes both advantages and limitations starting from simple fake image detection to AI synthesized image detection approaches that are available in the literature. Generative Adversarial Network (GAN) is the trending algorithm for artificial image synthesis, because the faces generated by GAN are highly realistic. As discriminators are already present in the GAN’s structure, any attempt to create a distinguisher that detects fake images synthesized by GAN, needs to structure itself to detect all existing patterns of fake image synthesis including that of GAN.
References
A. Kumar, L. Bi, J. Kim, and D. D. Feng, “Machine learning in medical imaging,” Biomedical Information Technology, pp. 167–196, 2020, doi: 10.1016/B978-0-12-816034-3.00005-5.
R. Nasina and S. Kommareddy, “FACE IMAGE METAMORPHOSIS OR MORPHING.”
R. Shankar, A. Srivastava, G. Gupta, R. Jadhav, and U. Thorate, “Fake Image Detection Using Machine Learning,” 2020.[Online]. Available: www.ijcrt.org
V. Gopal Edupuganti and F. Y. Shih, “Authentication of JPEG Images Based on Genetic Algorithms,” 2010.
H.-J. Lin, C.-W. Wang, and Y.-T. Kao, “Fast Copy-Move Forgery Detection.”[Online]. Available: http://int.chihlee.edu.tw
S. Math and R. C. Tripathi, “IMAGE QUALITY FEATURE BASED DETECTION ALGORITHM FOR FORGERY IN IMAGES,” 2011.
A. Al-Rammahi, N. el Abbadi, A. M. Hassan, and M. Al-Nwany, “Blind Fake Image detection,” 2013.[Online]. Available: www.IJCSI.org
N. A. N. Azhan, R. A. Ikuesan, S. A. Razak, and V. R. Kebande, “Error Level Analysis Technique for Identifying JPEG Block Unique Signature for Digital Forensic Analysis,” Electronics (Switzerland), vol. 11, no. 9, 2022, doi: 10.3390/electronics11091468.
N. Kanwal, J. Singh Bhullar, A. Girdhar, and L. Kaur, “Detection of Digital Image Forgery using Fast Fourier Transform and Local Features.”
Asif Razzaq, “Microsoft AI Research Introduces A Huge Synthetic-Face Dataset Along With A Face Analysis Method Using Synthetic Data Alone,” Marktechpost LLC, Oct. 04, 2021.
M. Lee and J. Seok, “Controllable generative adversarial network,” IEEE Access, vol. 7, pp. 28158–28169, 2019, doi: 10.1109/ACCESS.2019.2899108.
G. Zhong, W. Gao, Y. Liu, Y. Yang, D. H. Wang, and K. Huang, “Generative adversarial networks with decoder–encoder output noises,” Neural Networks, vol. 127, pp. 19–28, Jul. 2020, doi: 10.1016/j.neunet.2020.04.005.
A. Radford, L. Metz, and S. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” Nov. 2015,[Online]. Available: http://arxiv.org/abs/1511.06434
P. Shamsolmoali et al., “Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies,” Dec. 2020,[Online]. Available: http://arxiv.org/abs/2012.13736
Y. Tian, X. Peng, L. Zhao, S. Zhang, and D. N. Metaxas, “CR-GAN: Learning Complete Representations for Multi-view Generation,” Jun. 2018,[Online]. Available: http://arxiv.org/abs/1806.11191
Y. Choi, M. Choi, M. Kim, J.-W. Ha, S. Kim, and J. Choo, “StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation,” Nov. 2017,[Online]. Available: http://arxiv.org/abs/1711.09020
F. Zhan, H. Zhu, and S. Lu, “Spatial Fusion GAN for Image Synthesis.”
Z. Zhang, Y. Song, and H. Qi, “Age Progression/Regression by Conditional Adversarial Autoencoder.”[Online]. Available: https://zzutk.github.io/Face-Aging-CAAE
G. Antipov, M. Baccouche, and J.-L. Dugelay, “Face Aging With Conditional Generative Adversarial Networks,” Feb. 2017,[Online]. Available: http://arxiv.org/abs/1702.01983
L. Tran, X. Yin, and X. Liu, “Disentangled Representation Learning GAN for Pose-Invariant Face Recognition.”
S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in 32nd International Conference on Machine Learning, ICML 2015, 2015, vol. 1, pp. 448–456.
P. Isola, J.-Y. Zhu, T. Zhou, A. A. Efros, and B. A. Research, “Image-to-Image Translation with Conditional Adversarial Networks.”[Online]. Available: https://github.com/phillipi/pix2pix.
J.-Y. Zhu, T. Park, P. Isola, A. A. Efros, and B. A. Research, “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks Monet Photos.”[Online]. Available: https://github.com/junyanz/CycleGAN.
J. Johnson, A. Alahi, and L. Fei-Fei, “Perceptual Losses for Real-Time Style Transfer and Super-Resolution.”
H.-Y. Fish Tung, A. W. Harley, W. Seto, and K. Fragkiadaki, “Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision.”
S. Benaim and L. Wolf, “One-Sided Unsupervised Domain Mapping.”[Online]. Available: https://github.com/sagiebenaim/DistanceGAN.
X. Zhang, S. Karaman, and S.-F. Chang, “Detecting and Simulating Artifacts in GAN Fake Images,” Jul. 2019,[Online]. Available: http://arxiv.org/abs/1907.06515
Z. Liu, X. Qi, and P. H. S. Torr, “Global Texture Enhancement for Fake Face Detection In the Wild.”
X. Wang, H. Guo, S. Hu, M.-C. Chang, and S. Lyu, “GAN-generated Faces Detection: A Survey and New Perspectives (2022),” Feb. 2022,[Online]. Available: http://arxiv.org/abs/2202.07145
H. Chi, I. Seop Na, S. Kim, N.-T. Do, I.-S. Na, and S.-H. Kim, “Forensics Face Detection From GANs Using Convolutional Neural Network,” 2018.[Online]. Available: https://www.researchgate.net/publication/327905310
K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Sep. 2014,[Online]. Available: http://arxiv.org/abs/1409.1556
X. Liu and X. Chen, “A Survey of GAN-Generated Fake Faces Detection Method Based on Deep Learning,” Journal of Information Hiding and Privacy Protection, vol. 2, no. 2, pp. 87–94, 2020, doi: 10.32604/jihpp.2020.09839.
Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman, “VGGFace2: A dataset for recognising faces across pose and age,” in Proceedings - 13th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2018, Jun. 2018, pp. 67–74. doi: 10.1109/FG.2018.00020.
C. C. Hsu, Y. X. Zhuang, and C. Y. Lee, “Deep fake image detection based on pairwise learning,” Applied Sciences (Switzerland), vol. 10, no. 1, Jan. 2020, doi: 10.3390/app10010370.
V. Wesselkamp, K. Rieck, D. Arp, and E. Quiring, “Misleading Deep-Fake Detection with GAN Fingerprints,” May 2022,[Online]. Available: http://arxiv.org/abs/2205.12543
M. T. Jafar, M. Ababneh, M. Al-Zoube, and A. Elhassan, “Digital Forensics and Analysis of Deepfake Videos,” in 2020 11th International Conference on Information and Communication Systems, ICICS 2020, Apr. 2020, pp. 53–58. doi: 10.1109/ICICS49469.2020.239493.
T. Wang, H. Cheng, K. P. Chow, and L. Nie, “Deep Convolutional Pooling Transformer for Deepfake Detection,” Sep. 2022,[Online]. Available: http://arxiv.org/abs/2209.05299
K. Sun, T. Yao, S. Chen, S. Ding, J. Li, and R. Ji, “Dual Contrastive Learning for General Face Forgery Detection.”[Online]. Available: www.aaai.org
Y. Luo, Y. Zhang, J. Yan, and W. Liu, “Generalizing Face Forgery Detection with High-frequency Features,” Mar. 2021,[Online]. Available: http://arxiv.org/abs/2103.12376
H. Zhao, T. Wei, W. Zhou, W. Zhang, D. Chen, and N. Yu, “Multi-attentional Deepfake Detection,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 2185–2194. doi: 10.1109/CVPR46437.2021.00222.