A Median Filtering Forensics Approach Based on Machine Learning

  • Bin Yang
  • Zhenyu Li
  • Weifeng Hu
  • Enguo Cao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10603)


Today manipulation of digital images has become easy due to powerful computers, advanced photo-editing software and high resolution capturing devices. Verifying the integrity of images without extra prior knowledge of the image content is an important research field. Since some general post-operations, like widely used median filtering, can affect the reliability of forensic methods in various ways, it is also significant to detect them. Current image median filtering forensics algorithms mainly extract features manually. In this paper, we present a new image forgery detection method based on machine learning, which utilizes a convolutional neural networks (CNN) to automatically learn hierarchical representations from the input images. A modified CNN architecture is specifically designed to identify traces left by the manipulation. The experimental results on several public datasets show that the proposed CNN based model outperforms some state-of-the-art methods.


Deep learning Median filtering forensics Convolutional neural networks Forgery detection Approach design 



This work is supported in part by the National Natural Science Foundation of China (Grant NO. 51505191), Jiangsu Province Natural Science Foundation of China (Grant NO. BK20150161), the Fundamental Research Funds for the Central Universities (NOs. JUSRP11534, JUSRP51642A).


  1. 1.
    Amerini, I., Ballan, L., Caldelli, R., Del Bimbo, A., Serra, G.: A SIFT-based forensic method for copy-move attack detection and transformation recovery. IEEE Trans. Inf. Forensics Secur. 6, 1099–1110 (2011)CrossRefGoogle Scholar
  2. 2.
    Mahdian, B., Saic, S.: Using noise inconsistencies for blind image forensics. Image Vis. Comput. 27, 1497–1503 (2009)CrossRefGoogle Scholar
  3. 3.
    Fu, Z., Ren, K., Shu, J., Sun, X., Huang, F.: Enabling personalized search over encrypted outsourced data with efficiency improvement. IEEE Trans. Parallel Distrib. Syst. 27, 2546–2559 (2016)CrossRefGoogle Scholar
  4. 4.
    Qu, Z., Keeney, J., Robitzsch, S., Zaman, F., Wang, X.: Multilevel pattern mining architecture for automatic network monitoring in heterogeneous wireless communication networks. Chin. Commun. 13, 108–116 (2016)Google Scholar
  5. 5.
    Xue, Y., Jiang, J., Zhao, B., Ma, T.: A self-adaptive artificial bee colony algorithm based on global best for global optimization. Soft Comput. 8, 1–18 (2017)Google Scholar
  6. 6.
    Yang, B., Sun, X., Guo, H., Xia, Z., Chen, X.: A copy-move forgery detection method based on CMFD-SIFT. Multimedia Tools Appl. 1–19 (2017)Google Scholar
  7. 7.
    Yang, B., Sun, X., Xin, X., Hu, W., Wu, Y.: Image copy–move forgery detection based on sped-up robust features descriptor and adaptive minimal–maximal suppression. J. Electron. Imag. 24, 063016 (2015)CrossRefGoogle Scholar
  8. 8.
    Yang, B., Sun, X., Chen, X., Zhang, J., Li, X.: Exposing photographic splicing by detecting the inconsistencies in shadows. Comput. J. 58, 588–600 (2014)CrossRefGoogle Scholar
  9. 9.
    Liu, Q., Chen, Z.: Improved approaches with calibrated neighboring joint density to steganalysis and seam-carved forgery detection in JPEG images. ACM Trans. Intell. Syst. Technol. 5, 1–30 (2014)Google Scholar
  10. 10.
    Mahdian, B., Saic, S.: Blind authentication using periodic properties of interpolation. IEEE Trans. Inf. Forensics Secur. 3, 529–538 (2008)CrossRefGoogle Scholar
  11. 11.
    Kirchner, M., Fridrich, J.: On detection of median filtering in digital images. In: Media Forensics and Security II, p. 754110 (2010)Google Scholar
  12. 12.
    Cao, G., Zhao, Y., Ni, R., Yu, L., Tian, H.: Forensic detection of median filtering in digital images. In: IEEE International Conference on Multimedia and Expo, pp. 89–94 (2010)Google Scholar
  13. 13.
    Yuan, H.D.: Blind forensics of median filtering in digital images. IEEE Trans. Inf. Forensics Secur. 6, 1335–1345 (2011)CrossRefGoogle Scholar
  14. 14.
    Kang, X., Stamm, M.C., Peng, A., Liu, K.J.R.: Robust median filtering forensics using an autoregressive model. IEEE Trans. Inf. Forensics Secur. 8, 1456–1468 (2013)CrossRefGoogle Scholar
  15. 15.
    Liu, A., Zhao, Z., Zhang, C., Su, Y.: Smooth filtering identification based on convolutional neural networks. Multimedia Tools Appl. 1–15 (2016)Google Scholar
  16. 16.
    Zhang, Y., Li, S., Wang, S., Shi, Y.Q.: Revealing the traces of median filtering using high-order local ternary patterns. IEEE Sig. Process. Lett. 21, 275–279 (2014)CrossRefGoogle Scholar
  17. 17.
    Peter, O.C., Daniel, N., Liu, S.C., Tobi, D., Michael, P.: Real-time classification and sensor fusion with a spiking deep belief network. Frontiers Neurosci. 7, 178 (2013)Google Scholar
  18. 18.
    Deng, L., Seltzer, M.L., Yu, D., Acero, A., Mohamed, A.R., Hinton, G.E.: Binary coding of speech spectrograms using a deep auto-encoder. In: INTERSPEECH 2010, Conference of the International Speech Communication Association, pp. 1692–1695, Makuhari, Chiba, Japan, September 2010Google Scholar
  19. 19.
    Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. Eprint Arxiv, vol. 1 (2014)Google Scholar
  20. 20.
    Chen, J., Kang, X., Liu, Y., Wang, Z.J.: Median filtering forensics based on convolutional neural networks. IEEE Sig. Process. Lett. 22, 1849–1853 (2015)CrossRefGoogle Scholar
  21. 21.
    Bayar, B., Stamm, M.C.: A deep learning approach to universal image manipulation detection using a new convolutional layer. In: ACM Workshop on Information Hiding and Multimedia Security, pp. 5–10 (2016)Google Scholar
  22. 22.
    Zhang, Y., Win, L.L., Goh, J., Thing, V.L.L.: Image region forgery detection: a deep learning approach (2016)Google Scholar
  23. 23.
    Yang, B., Sun, X., Chen, X., Zhang, J., Li, X.: An efficient forensic method for copy-move forgery detection based on DWT-FWHT. Radioengineering 22, 1098–1105 (2013)Google Scholar
  24. 24.
    Li, S., Liu, Z.Q., Chan, A.B.: Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network. Int. J. Comput. Vis. 113, 19–36 (2015)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)zbMATHMathSciNetGoogle Scholar
  26. 26.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning, pp. 807–814 (2010)Google Scholar
  27. 27.
    Haykin, S., Kosko, B.: Gradient based learning applied to document recognition. Wiley-IEEE Press (2009)Google Scholar
  28. 28.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  29. 29.
    Bas, P., Filler, T., Pevný, T.: “Break our steganographic system”: the ins and outs of organizing BOSS. In: Filler, T., Pevný, T., Craver, S., Ker, A. (eds.) IH 2011. LNCS, vol. 6958, pp. 59–70. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-24178-9_5 CrossRefGoogle Scholar
  30. 30.
    Schaefer, G., Stich, M.: UCID: an uncompressed color image database, vol. 5307, pp. 472–480 (2004)Google Scholar
  31. 31.
    Dong, J., Wang, W., Tan, T.: CASIA image tampering detection evaluation database. In: IEEE China Summit and International Conference on Signal and Information Processing, pp. 422–426 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of DesignJiangnan UniversityWuxiChina

Personalised recommendations