Skip to main content
SpringerLink
Log in

A deep learning approach with data augmentation for median filtering forensics

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Median filtering forensics for small-size JPEG compressed images is practicable and useful in the block-based tampering detection. In this paper, we concentrate the detection of median filtering for small-size JPEG compressed images. Such a task is chanllenging because it is difficult to learn effective and reliable feature from insufficient and subtle median filtering traces left in the small-size JPEG compressed images. We propose a median filtering forensics network called MFFNet to solve these problems, which is driven by both deep convolutional neural network (CNN) and data augmention. Since median filtering forensics is essentially a binary classification task, we borrow a powerful image classification model Xception as the base model to construct the proposed MFFNet. In order to enhance the weak traces of median filtering left in the small-size JPEG compressed images, we carefully simplify and re-design the architecture of Xception, among which the pre-processing layers containing up-scaling and extracting residuals, pooling layers and squeeze-and-excitation block are employed. In addition, a large number of training images along with data augmentation are also employed to improve the generalization ablilty of the MFFNet. The extensive experimental results on the composite database demonstrate that the proposed approach outperforms the state-of-the-arts, achieveing at least 4% higher detection accuracy for detecting median filtering on 32 × 32 JPEG 70 compressed images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. [Online] <http://exile.felk.cvut.cz/boss/BOSSFinal/index.php?mode=VIEW&tmpl=materials>

  2. [Online] <http://photogallery.nrcs.usda.gov >

  3. Barni M, Cancelli G, Esposito A (2010) Forensics aided steganalysis of heterogeneous images. In: 2010 IEEE international conference on acoustics, speech and signal processing, pp 1690–1693

    Chapter  Google Scholar 

  4. Bas P, Furon T (2008) BOWS-2 contest (break our watermarking system). In: Organised within the activity of the watermarking virtual laboratory (Wavila) of the European network of excellence ECRYPT

    Google Scholar 

  5. Bas P, Filler T, Pevný T (2011) Break our steganographic system: the ins and outs of organizing BOSS. In: International workshop on information hiding. Springer, Berlin, Heidelberg, pp 59–70

    Chapter  Google Scholar 

  6. Bayar B, Stamm MC (2018) Constrained convolutional neural networks: a new approach towards general purpose image manipulation detection. IEEE Transactions on Information Forensics and Security 13(11):2691–2706

    Article  Google Scholar 

  7. Bovik ALANCONRAD (1987) Streaking in median filtered images. IEEE Trans Acoust Speech Signal Process 35(4):493–503

    Article  MATH  Google Scholar 

  8. Cao G, Zhao Y, Ni R, Yu L, Tian H (2010) Forensic detection of median filtering in digital images. In: 2010 IEEE international conference on multimedia and expo. IEEE, pp 89–94

    Chapter  Google Scholar 

  9. Chen C, Ni J, Huang R, Huang J (2012) Blind median filtering detection using statistics in difference domain. In: International workshop on information hiding. Springer, Berlin, Heidelberg, pp 1–15

    Google Scholar 

  10. Chen J, Kang X, Liu Y, Wang ZJ (2015) Median filtering forensics based on convolutional neural networks. IEEE Signal Process Lett 22(11):1849–1853

    Article  Google Scholar 

  11. Chen Y, Lyu ZX, Kang X, Wang ZJ (2018) A rotation-invariant convolutional neural network for image enhancement forensics. In: In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2111–2115

    Chapter  Google Scholar 

  12. Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258

    Google Scholar 

  13. Chuang WH, Swaminathan A, Wu M (2009) Tampering identification using empirical frequency response. In: 2009 IEEE international conference on acoustics, speech and signal processing. IEEE, pp 1517–1520

    Chapter  Google Scholar 

  14. Dang-Nguyen DT, Pasquini C, Conotter V, Boato G (2015) Raise: a raw images dataset for digital image forensics. In: Proceedings of the 6th ACM multimedia systems conference, pp 219–224

    Chapter  Google Scholar 

  15. Dozat, T. (2016). Incorporating nesterov momentum into adam.

    Google Scholar 

  16. Duan G, Miao J, Huang T (2019) Median filtering detection of small-size image using AlexCaps-network. In: International workshop on digital watermarking. Springer, Cham, pp 126–140

    Google Scholar 

  17. Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security 7(3):868–882

    Article  Google Scholar 

  18. Gloe T, Böhme R (2010) The'Dresden image Database'for benchmarking digital image forensics. In: Proceedings of the 2010 ACM symposium on applied computing, pp 1584–1590

    Chapter  Google Scholar 

  19. He K, Zhang X, Ren S, Sun J (2016a) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

    Google Scholar 

  20. He K, Zhang X, Ren S, Sun J (2016b) Identity mappings in deep residual networks. In: European conference on computer vision. Springer, Cham, pp 630–645

    Google Scholar 

  21. Heydarpoor F, Abbasi E, Ebadi MJ, Karbassi M (2020) Solving an optimal control problem of Cancer treatment by artificial neural networks. International Journal of Interactive Multimedia and Artificial Intelligence 6(4):18–25

    Article  Google Scholar 

  22. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141

    Google Scholar 

  23. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708

    Google Scholar 

  24. Jin X, Jing P, Su Y (2018) AMFNet: an adversarial network for median filtering detection. IEEE Access 6:50459–50467

    Article  Google Scholar 

  25. Kang X, Stamm MC, Peng A, Liu KR (2013) Robust median filtering forensics using an autoregressive model. IEEE Transactions on Information Forensics and Security 8(9):1456–1468

    Article  Google Scholar 

  26. Kim D, Jang HU, Mun SM, Choi S, Lee HK (2017) Median filtered image restoration and anti-forensics using adversarial networks. IEEE Signal Process Lett 25(2):278–282

    Article  Google Scholar 

  27. Kirchner M, Fridrich J (2010) On detection of median filtering in digital images. In: Media forensics and security II (Vol. 7541, p. 754110). International Society for Optics and Photonics

    Google Scholar 

  28. Kodovský J, Fridrich J (2014) Effect of image downsampling on steganographic security. IEEE Trans Inf Forensics Secur 9(5):752–762

    Article  Google Scholar 

  29. Li H, Luo W, Qiu X, Huang J (2016) Identification of various image operations using residual-based features. IEEE Trans Circuits Syst Video Technol 28(1):31–45

    Article  Google Scholar 

  30. Lin, M., Chen, Q., & Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400.

    Google Scholar 

  31. Liu A, Zhao Z, Zhang C, Su Y (2017) Median filtering forensics in digital images based on frequency-domain features. Multimed Tools Appl 76(21):22119–22132

    Article  Google Scholar 

  32. Liu A, Zhao Z, Zhang C, Su Y (2019) Smooth filtering identification based on convolutional neural networks. Multimed Tools Appl:1–15

  33. Luo S, Peng A, Zeng H, Kang X, Liu L (2019) Deep residual learning using data augmentation for median filtering forensics of digital images. IEEE Access 7:80614–80621

    Article  Google Scholar 

  34. Niu Y, Zhao Y, Ni R (2017) Robust median filtering detection based on local difference descriptor. Signal Process Image Commun 53:65–72

    Article  Google Scholar 

  35. Patterson G, Hays J (2016) Coco attributes: attributes for people, animals, and objects. In: European conference on computer vision. Springer, Cham, pp 85–100

    Google Scholar 

  36. Peng A, Kang X (2016) Median filtering forensics based on multi-directional difference of filtering residuals. Jisuanji Xuebao/Chin. J Comput 39(3):503–515

    MathSciNet  Google Scholar 

  37. Peng A, Luo S, Zeng H, Wu Y (2019) Median filtering forensics using multiple models in residual domain. IEEE Access 7:28525–28538

    Article  Google Scholar 

  38. Pevny T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inf Forensics Secur 5(2):215–224

    Article  Google Scholar 

  39. Schaefer G, Stich M (2003) UCID: an uncompressed color image database. In: Storage and retrieval methods and applications for multimedia 2004 (Vol. 5307, pp. 472-480). International Society for Optics and Photonics

    Google Scholar 

  40. Shan W, Yi Y, Qiu J, Yin A (2019) Robust median filtering forensics using image deblocking and filtered residual fusion. IEEE Access 7:17174–17183

    Article  Google Scholar 

  41. Shen Z, Ni J, Chen C (2016) Blind detection of median filtering using linear and nonlinear descriptors. Multimed Tools Appl 75(4):2327–2346

    Article  Google Scholar 

  42. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

  43. Stamm MC, Liu KR (2011) Anti-forensics of digital image compression. IEEE Trans Inf Forensics Secur 6(3):1050–1065

    Article  Google Scholar 

  44. Stamm MC, Wu M, Liu KR (2013) Information forensics: an overview of the first decade. IEEE Access 1:167–200

    Article  Google Scholar 

  45. Takahashi R, Matsubara T, Uehara K (2018) Ricap: random image cropping and patching data augmentation for deep cnns. In: Asian conference on machine learning, pp 786–798

    Google Scholar 

  46. Tan, M., & Le, Q. V. (2019). Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946

  47. Tang H, Ni R, Zhao Y, Li X (2018) Median filtering detection of small-size image based on CNN. J Vis Commun Image Represent 51:162–168

    Article  Google Scholar 

  48. Tariang DB, Chakraborty RS, Naskar R (2019) A robust residual dense neural network for countering Antiforensic attack on median filtered images. IEEE Signal Process Lett 26(8):1132–1136

    Article  Google Scholar 

  49. Yang J, Ren H, Zhu G, Huang J, Shi YQ (2018) Detecting median filtering via two-dimensional AR models of multiple filtered residuals. Multimed Tools Appl 77(7):7931–7953

    Article  Google Scholar 

  50. Yu L, Zhang Y, Han H, Zhang L, Wu F (2019) Robust median filtering forensics by cnn-based multiple residuals learning. IEEE Access 7:120594–120602

    Article  Google Scholar 

  51. Yuan HD (2011) Blind forensics of median filtering in digital images. IEEE Trans Inf Forensics Secur 6(4):1335–1345

    Article  Google Scholar 

  52. Zhan Y, Chen Y, Zhang Q, Kang X (2017) Image forensics based on transfer learning and convolutional neural network. In: Proceedings of the 5th ACM workshop on information hiding and multimedia security, pp 165–170

    Chapter  Google Scholar 

  53. Zhang Y, Li S, Wang S, Shi YQ (2014) Revealing the traces of median filtering using high-order local ternary patterns. IEEE Signal Process Lett 21(3):275–279

    Article  Google Scholar 

  54. Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412.

  55. Zhang J, Liao Y, Zhu X, Wang H, Ding J (2020) A deep learning approach in the discrete cosine transform domain to median filtering forensics. IEEE Signal Process Lett 27:276–280

    Article  Google Scholar 

  56. Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: AAAI, pp 13001–13008

    Google Scholar 

Download references

Acknowledgements

This work was partially supported by NSFC (No. 61702429), Sichuan Science and Technology Program (No. 21ZDYF3119).

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Southwest University of Science and Technology, Mian Yang, 621010, China

    Wanli Dong, Hui Zeng, Yong Peng, Xiaoming Gao & Anjie Peng

Authors
  1. Wanli Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hui Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yong Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaoming Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Anjie Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anjie Peng.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dong, W., Zeng, H., Peng, Y. et al. A deep learning approach with data augmentation for median filtering forensics. Multimed Tools Appl 81, 11087–11105 (2022). https://doi.org/10.1007/s11042-022-12040-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12040-w

Keywords

Search

Navigation