Advertisement

Journal of Real-Time Image Processing

, Volume 16, Issue 3, pp 725–740 | Cite as

A multi-purpose image forensic method using densely connected convolutional neural networks

  • Yifang Chen
  • Xiangui KangEmail author
  • Yun Q. Shi
  • Z. Jane Wang
Special Issue Paper
  • 169 Downloads

Abstract

Multi-purpose forensics is attracting increasing attention worldwide. In this paper, we propose a multi-purpose method based on densely connected convolutional neural networks (CNNs) for simultaneous detection of 11 different types of image manipulations. An efficient CNN structure has been specifically designed for forensics by considering vital architecture components, including the number of convolutional layers, the size of convolutional kernels, the nonlinear activations, and the type of pooling layer. The dense connectivity pattern, which has better parameter efficiency than the traditional pattern, is explored to strengthen the propagation of features related to image manipulation detection. When compared with four state-of-the-art methods, our experiments demonstrate that the proposed CNN architecture can achieve better performance in multiple operation detections for different image sizes, especially on small image patches. Consequently, the proposed method can accurately detect local image manipulations. The proposed method can achieve better overall performance when tested on different databases as well as better robustness against JPEG compression even under low-quality JPEG compression.

Keywords

Image forensics Convolutional neural network Dense connectivity Multi-purpose forensics 

Notes

Acknowledgements

This work was supported by NSFC (Grant nos. U1536204, 61772571, 61702429).

References

  1. 1.
    Cao, G., Zhao, Y., Ni, R.: Detection of image sharpening based on histogram aberration and ringing artifacts. In: Proc. IEEE Int. conf. on multimedia and expo, New York, USA, pp. 1026–1029 (2009)Google Scholar
  2. 2.
    Cao, G., Zhao, Y., Ni, R., Kot, A.C.: Unsharp masking sharpening detection via overshoot artifacts analysis. IEEE Signal Process. Lett. 18(10), 603–606 (2011)CrossRefGoogle Scholar
  3. 3.
    Cao, G., Zhao, Y., Ni, R., Li, X.: Contrast enhancement-based forensics in digital images. IEEE Trans. Inf. Forensics Secur. 9(3), 515–525 (2014)CrossRefGoogle Scholar
  4. 4.
    Singh, N., Gupta, A., Jain, R.C.: Adaptive histogram equalization based image forensics using statistics of DC DCT coefficients. Digital Image Process. Comput. Graph. 16(1), 125–134 (2018)Google Scholar
  5. 5.
    Kirchner, M., Fridrich, J.: On detection of median filtering in digital images. Proc. SPIE Media Forensics Secur. II Part IS&T-SPIE Electron. Imaging Symp. 7541, 754110 (2010)Google Scholar
  6. 6.
    Yuan, H.D.: Blind forensics of median filtering in digital images. IEEE Trans. Inf. Forensics Secur. 6(4), 1335–1345 (2011)CrossRefGoogle Scholar
  7. 7.
    Popescu, A.C., Farid, H.: Exposing digital forgeries by detecting traces of resampling. IEEE Trans. Signal Process. 53(2), 758–767 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Luo, W., Huang, J., Qiu, G.: JPEG error analysis and its applications to digital image forensics. IEEE Trans. Inf. Forensics Secur. 5(3), 480–491 (2010)CrossRefGoogle Scholar
  9. 9.
    Bianchi, T., Piva, A.: Detection of nonaligned double JPEG compression based on integer periodicity maps. IEEE Trans. Inf Forensics Secur 7(2), 842–848 (2012)CrossRefGoogle Scholar
  10. 10.
    Qiu, X., Li, H., Luo, W., Huang, J.: A universal image forensic strategy based on steganalytic model. In: Proc. ACM workshop on information hiding and multimedia security, Salzburg, Austria, pp. 165–170 (2014)Google Scholar
  11. 11.
    Fan, W., Wang, K., Cayre, F.: General-purpose image forensics using patch likelihood under image statistical models. In: Proc. IEEE Int. workshop on information forensics and security, Rome, Italy, pp. 1–6 (2015)Google Scholar
  12. 12.
    Zeng, H., Kang, X., Peng, A.: A multi-purpose countermeasure against image anti-forensics using autoregressive model. Neurocomputing 189, 117–122 (2016)CrossRefGoogle Scholar
  13. 13.
    Li, H., Luo, W., Qiu, X., Huang, J.: Identification of various image operations using residual-based features. IEEE Trans. Circ Syst Video Technol 28(1), 31–45 (2016)CrossRefGoogle Scholar
  14. 14.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, Lake Tahoe, USA, pp. 1097–1105 (2012)Google Scholar
  15. 15.
    Swietojanski, P., Ghoshal, A., Renals, S.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142–158 (2016)CrossRefGoogle Scholar
  16. 16.
    Chen, J., Kang, X., Liu, Y., Wang, Z.J.: Median filtering forensics based on convolutional neural networks. IEEE Signal Process. Lett. 22(11), 1849–1853 (2015)CrossRefGoogle Scholar
  17. 17.
    Yu, J., Zhan, Y., Yang, J., Kang, X.: A multi-purpose image counter-antiforensic method using convolutional neural networks. In: Proc. 16th Int. Workshop on Digital Forensics and Watermarking, Beijing, China, pp. 3–15 (2016)Google Scholar
  18. 18.
    Bondi, L., Guera, D., Bestagini, P., Delp, E.J., Tubaro, S.: First steps toward camera model identification with convolutional neural networks. IEEE Signal Process. Lett. 24(3), 259–263 (2017)CrossRefGoogle Scholar
  19. 19.
    Bayar, B., Stamm, M.C.: Constrained convolutional neural networks: a new approach towards general purpose image manipulation detection. IEEE Trans. Inf. Forensics Secur. 13, 1556–6013(c) 2018CrossRefGoogle Scholar
  20. 20.
    Chen, Y., Lyu, Z., Kang, X., Wang, Z.J.: A rotation-invariant convolutional neural network for image enhancement forensics. In: Proc. IEEE Int. Conf. on acoustics, speech and signal processing, Calgary, Canada, pp. 2111–2115 (2018)Google Scholar
  21. 21.
    Chen, Y., Kang, X., Wang, Z.J., Zhang, Q.: Densely connected convolutional neural network for multi-purpose image forensics under anti-forensic attacks. In: Proc. ACM workshop on information hiding and multimedia security, Innsbruck, Austria, pp. 91–96 (2018)Google Scholar
  22. 22.
    Liu, Y., Guan, Q., Zhao, X., Cao, Y.: Image forgery localization based on multi-scale convolutional neural networks. In: Proc. ACM workshop on information hiding and multimedia security, Innsbruck, Austria, pp. 85–90 (2018)Google Scholar
  23. 23.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proc. IEEE conf. on computer vision and pattern recognition, Honolulu, USA, pp. 770–778 (2016)Google Scholar
  24. 24.
    He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Proc. European conf. on computer vision, Amsterdam, Netherlands, pp. 630–645 (2016)Google Scholar
  25. 25.
    Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Proc. European conf. on computer vision, Amsterdam, Netherlands, pp. 646–661 (2016)Google Scholar
  26. 26.
    Larsson, G., Maire, M., Shakhnarovich, G.: Fractalnet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)Google Scholar
  27. 27.
    Huang, G., Liu, Z., Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proc. IEEE Conf. on computer vision and pattern recognition, Hawaii, USA, pp. 77–86 (2017)Google Scholar
  28. 28.
    Yang, J., Shi, Y., Wong, E.K., Kang, X.: JPEG steganalysis based on DenseNet. arXiv preprint arXiv: 1711.09335 (2017)Google Scholar
  29. 29.
    Stamm, M.C., Liu, K.J.R.: Anti-forensics of digital image compression. IEEE Trans. Inf. Forensics Secur. 6(3), 1050–1065 2011CrossRefGoogle Scholar
  30. 30.
    Xu, J., Ling, Y., Zheng, X.: Forensic detection of Gaussian low-pass filtering in digital images. In: Proc. 8th International congress on image and signal processing, Shenyang, China, pp. 819–823 (2015)Google Scholar
  31. 31.
    Chuang, W., Swaminathan, A., Wu, M.: Tampering identification using empirical frequency response. In: Proc. IEEE Int. conf. on acoustics, speech and signal processing, Taipei, Taiwan, pp. 1517–1520 (2009)Google Scholar
  32. 32.
    Hwang, J., Rhee, K.: Gaussian filtering detection based on features of residuals in image forensics. In: Proc. IEEE RIVF int. conf. on computing & communication technologies, research, innovation, and vision for the future, Hanoi, Vietnam, pp 153–157 (2016)Google Scholar
  33. 33.
    Qian, Y., Dong, J., Wang, W., Tan, T.: Deep learning for steganalysis via convolutional neural networks. In: Proc. SPIE, media watermarking, security, and forensics, San Jose, CA, USA, pp. 94090J0–94090J10 (2015)Google Scholar
  34. 34.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: proc. int. conf. on international conference on machine learning, Haifa, Israel, pp. 807–814 (2010)Google Scholar
  35. 35.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proc. int. conf. on international conference on machine learning, Lille, France, pp. 448–456 (2015)Google Scholar
  36. 36.
    Fridrich, J., Kodovsky, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Yifang Chen
    • 1
  • Xiangui Kang
    • 1
    Email author
  • Yun Q. Shi
    • 2
  • Z. Jane Wang
    • 3
  1. 1.Guangdong Key Lab of Information SecuritySun Yat-sen UniversityGuangzhouChina
  2. 2.Department of Electrical and Computer EngineeringNew Jersey Institute of TechnologyNewarkUSA
  3. 3.Department of Electrical and Computer EngineeringUniversity of British ColombiaVancouverCanada

Personalised recommendations