Abstract
Convolutional Neural Networks (CNNs) have become an effective tool to detect image manipulation operations, e.g., noise addition, median filtering and JPEG compression. In this paper, we propose a simple and practical method for adjusting the CNN’s first layer, based on a proper scaling of first-layer filters with a data-dependent approach. The key idea is to keep the stability of the variance of data flow in a CNN. We also present studies on the output variance for convolutional filter, which are the basis of our proposed scaling. The proposed method can cope well with different first-layer initialization algorithms and different CNN architectures. The experiments are performed with two challenging forensic problems, i.e., a multi-class classification problem of a group of manipulation operations and a binary detection problem of JPEG compression with high quality factor, both on relatively small image patches. Experimental results show the utility of our method with a noticeable and consistent performance improvement after scaling.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The 30 SRM filters can be found in the class of SrmFiller, starting from line 347 of this webpage https://github.com/tansq/WISERNet/blob/master/filler.hpp.
References
Bayar, B., Stamm, M.C.: Constrained convolutional neural networks: a new approach towards general purpose image manipulation detection. IEEE Trans. Inf. Forensics Secur. 13(11), 2691–2706 (2018)
Castillo Camacho, I., Wang, K.: A simple and effective initialization of CNN for forensics of image processing operations. In: Proceedings of the ACM Workshop on Information Hiding and Multimedia Security, Paris, France, pp. 107–112 (2019)
Chen, B., Li, H., Luo, W., Huang, J.: Image processing operations identification via convolutional neural network. Sci. China Inf. Sci. 63(3) (2020). https://doi.org/10.1007/s11432-018-9492-6
Chen, J., Kang, X., Liu, Y., Wang, Z.J.: Median filtering forensics based on convolutional neural networks. IEEE Sig. Process. Lett. 22(11), 1849–1853 (2015)
Fridrich, J., Kodovský, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)
Gloe, T., Böhme, R.: The Dresden image database for benchmarking digital image forensics. In: Proceedings of the ACM Symposium on Applied Computing, Sierre, Switzerland, pp. 1584–1590 (2010)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, pp. 249–256 (2010)
Li, F.F., Johnson, J., Yeung, S.: Neural networks part 2: setting up the data and the loss (2018). Course notes of Stanford University “CS231n: Convolutional Neural Networks for Visual Recognition". http://cs231n.github.io/neural-networks-2/. Accessed 16 Dec 2020
Li, H., Huang, J.: Localization of deep inpainting using high-pass fully convolutional network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8301–8310 (2019)
Liu, Y., Guan, Q., Zhao, X., Cao, Y.: Image forgery localization based on multi-scale convolutional neural networks. In: Proceedings of the ACM Workshop on Information Hiding and Multimedia Security, Innsbruck, Austria, pp. 85–90 (2018)
Simoncelli, E.P., Olshausen, B.A.: Natural image statistics and neural representation. Ann. Rev. Neurosci. 24(1), 1193–1216 (2001)
Acknowledgments
This work is partially funded by the French National Research Agency (DEFALS ANR-16-DEFA-0003, ANR-15-IDEX-02) and the Mexican National Council of Science and Technology (CONACYT).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Castillo Camacho, I., Wang, K. (2021). Data-Dependent Scaling of CNN’s First Layer for Improved Image Manipulation Detection. In: Zhao, X., Shi, YQ., Piva, A., Kim, H.J. (eds) Digital Forensics and Watermarking. IWDW 2020. Lecture Notes in Computer Science(), vol 12617. Springer, Cham. https://doi.org/10.1007/978-3-030-69449-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-69449-4_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69448-7
Online ISBN: 978-3-030-69449-4
eBook Packages: Computer ScienceComputer Science (R0)