Abstract
The recent and rapid growth in image manipulation techniques raises grave concerns with respect to document forgery. It also diminishes trust in the data available publicly and can cause harm by spreading false information. In this paper, the problem of facial forgery by training a neural network to distinguish between real and fake faces has been addressed. The convolutional neural network has been trained with the help of transfer learning, which allows us to utilize computer vision models like ResNet and AlexNet, which were pre-trained on massive datasets. The network was evaluated on a dataset of 2041 images provided by the computational Intelligence and Photography Lab at the Department of Computer Science, Yonsei University. Results show that ResNet-152 is able to detect facial forgery with an accuracy of up to 76.79%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Neural information processing systems
Li J, Shen T, Zhang W, Ren H, Zeng D, Mei T (2019) Zooming into face forensics: a pixel-level analysis
Rössler A, Cozzolino D, Verdoliva L, Riess C, Thies J, Nießner M (2019) FaceForensics++: learning to detect manipulated facial images
Image recognition & image processing medium. https://medium.com/@Adoriasoft/image-recognition-and-image-processing-techniques-fe3d35d58919. Last accessed 2020/5/3
Xin Y et al (2018) Machine learning and deep learning methods for cybersecurity. IEEE Access 6:35365–35381
Transfer learning medium. https://towardsdatascience.com/a-comprehensive-hands-on-guide-to-transfer-learning-with-real-world-applications-in-deep-learning-212bf3b2f27a. Last accessed: 2020/5/5
Shin H et al (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35(5):1285–1298
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
Dai W, Yang Q, Xue G-R, Yu Y (2007) Boosting for transfer learning. In: ACM international conference proceeding series, 227
Boughorbel S, Jarray F, El-Anbari M (2017) Optimal classifier for imbalanced data using Matthews correlation coefficient metric. PLOS ONE 12:e0177678. https://doi.org/10.1371/journal.pone.0177678
Wen L, Xu D (2019) Face image manipulation detection. In: IOP conference series: materials science and engineering, 533, 012054. https://doi.org/10.1088/1757-899X/533/1/012054
Afchar D, Nozick V, Yamagishi J, Echizen I (2018) MesoNet: a compact facial video forgery detection network 1–7. https://doi.org/10.1109/WIFS.2018.8630761
Seibold C, Samek W, Hilsmann A, Eisert P (2017) Detection of face morphing attacks by deep learning 107–120. https://doi.org/10.1007/978-3-319-64185-0_9
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. IJCV
AlexNet medium. https://towardsdatascience.com/alexnet-the-architecture-that-challenged-cnns-e406d5297951. Last accessed: 2020/5/9
VGG medium. https://towardsdatascience.com/vgg-neural-networks-the-next-step-after-alexnet-3f91fa9ffe2c. Last accessed: 2020/5/15
ResNet and its variants medium. https://towardsdatascience.com/an-overview-of-resnet-and-its-variants-5281e2f56035. Last accessed: 2020/5/3
Forged faces dataset Kaggle. https://www.kaggle.com/ciplab/real-and-fake-face-detection. Last accessed: 2020/5/3
Fastai. https://docs.fast.ai/index.html. Last accessed: 2020/4/16
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chandani, K., Arora, M. (2021). Automatic Facial Forgery Detection Using Deep Neural Networks. In: Kumar, N., Tibor, S., Sindhwani, R., Lee, J., Srivastava, P. (eds) Advances in Interdisciplinary Engineering. Lecture Notes in Mechanical Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-15-9956-9_21
Download citation
DOI: https://doi.org/10.1007/978-981-15-9956-9_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9955-2
Online ISBN: 978-981-15-9956-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)