Forensics of visual privacy protection in digital images

  • Fei Xue
  • Wei LuEmail author
  • Honglin Ren
  • Huimei Xiao
  • Qin Zhang
  • Xianjin Liu


Visual privacy protection (VPP) is to protect individual’s privacy information in digital images or videos against being seen, such as portrait etc. Once being protected, the privacy may be imperceptible. Forensics of visual privacy protection is becoming a new challenge. As a main visual privacy protection technology, blur operation is always used in VPP. When using the existing approaches such as blur segmentation to detect the images, natural blur or other solid color regions will be falsely alarmed, resulting in low precision. In this paper, we present a novel metric invisibility degree (IvD) to measure the privacy protected blur degree of each pixel. The proposed IvD is defined by calculating the similarity between the test image and the re-blurred image in joint transformation and spatial domain, which could significantly enhance the difference between the privacy protected blur region and the other regions. Then, an effective method based on IvD is developed to automatically forensic and localize the visual privacy protection regions. Firstly, the IvD in block DCT domain of each pixel is calculated, and a IvD map is obtained. Secondly, using the IvD map, the test image is segmented and followed by morphological operation to decrease the mis-alarm regions. Finally, a spatial texture feature descriptor, including gray statistics, smoothness and information capacity, is developed, based on which the detection result is further refined. Experimental results show that the proposed method can detect the privacy regions accurately.


Digital image forensics Visual privacy protection Privacy protected blur Invisibility degree (IvD) 



This work is supported by the National Natural Science Foundation of China (No. U1736118), the Key Areas R&D Program of Guangdong (No. 2019B010136002), the Key Scientific Research Program of Guangzhou (No. 201804020068), the Natural Science Foundation of Guangdong (No. 2016A030313350), the Special Funds for Science and Technology Development of Guangdong (No. 2016KZ010103), Shanghai Minsheng Science and Technology Support Program (17DZ1205500), Shanghai Sailing Program (17YF1420000), the Fundamental Research Funds for the Central Universities (No. 16lgjc83 and No. 17lgjc45).


  1. 1.
    Avidan S, Butman M (2006) Blind vision. Lecture notes in computer science: 1–13Google Scholar
  2. 2.
    Bao L, Zhou Y (2015) Image encryption: Generating visually meaningful encrypted images. Inf Sci 324:197–207MathSciNetzbMATHCrossRefGoogle Scholar
  3. 3.
    Barni M, Bianchi T, Catalano D, Raimondo MD, Labati RD, Failla P, Fiore D, Lazzeretti R, Piuri V, Scotti F (2010) Privacy-preserving fingercode authentication. In: ACM workshop on multimedia and security, pp 231-240. New York, USAGoogle Scholar
  4. 4.
  5. 5.
    Cao G, Zhao Y, Ni R, Li X (2014) Contrast enhancement-based forensics in digital images. IEEE Trans Inf Foren Sec 9(3):515–525CrossRefGoogle Scholar
  6. 6.
    Chaaraoui AA, Climent-Pérez P, Flórez-Revuelta F (2012) A review on vision techniques applied to human behaviour analysis for ambient-assisted living. Expert Syst Appl 39(12):10873–10888CrossRefGoogle Scholar
  7. 7.
    Chaaraoui AA, Climent-Pérez P, Flórez-Revuelta F (2012) An efficient approach for multi-view human action recognition based on Bag-Of-Key-Poses. Springer, Berlin. CrossRefGoogle Scholar
  8. 8.
    Chen J, Lu W, Yeung Y, Xue Y, Liu X, Lin C, Zhang Y (2018) Binary image steganalysis based on distortion level co-occurrence matrix. Comput Mater Continua 55(2):201–211Google Scholar
  9. 9.
    Chen B, Wu X, Lu W, Ren H (2019) Reversible data hiding in encrypted images with additive and multiplicative public-key homomorphism. Signal Process 164:48–57. CrossRefGoogle Scholar
  10. 10.
    Cheung SCS, Paruchuri JK, Nguyen TP (2008) Managing privacy data in pervasive camera networks. In: IEEE International conference on image processing, pp 1676–1679Google Scholar
  11. 11.
    Cho S, Lee S (2009) Fast motion deblurring. ACM Transactions On Graphics 28(5):1–8CrossRefGoogle Scholar
  12. 12.
    Crete F, Nicolas M (2007) The blur effect: perception and estimation with a new no-reference perceptual blur metric. Proceedings of SPIE - The International Society for Optical Engineering 12:64920I-64920I-11Google Scholar
  13. 13.
    Erkin Z, Franz M, Guajardo J, Katzenbeisser S, Lagendijk I, Toft T (2009) Privacy-preserving face recognition. In: Privacy enhancing technologies, pp 235–253. Seattle, USACrossRefGoogle Scholar
  14. 14.
    Frome A, Cheung G, Abdulkader A, Zennaro M (2009) Large-scale privacy protection in google street view. In: IEEE International conference on computer vision, pp 2373–2380Google Scholar
  15. 15.
    Hu S, Wang Q, Wang J, Qin Z, Ren K (2016) Secsift: Privacy-preserving outsourcing computation of feature extractions over encrypted image data. IEEE Trans Image Process 25(7):3411–3425MathSciNetzbMATHCrossRefGoogle Scholar
  16. 16.
    Hu X, Zhang W, Hu H, Yu N (2014) Non-local denoising in encrypted images. In: International conference on internet of vehicles, pp 386–395. Beijing, ChinaGoogle Scholar
  17. 17.
    Hua Z, Zhou Y, Pun C, Chen CLP (2015) 2d sine logistic modulation map for image encryption. Inf Sci 297:80–94CrossRefGoogle Scholar
  18. 18.
    Huang X, Liu Z, Lu W, Liu H, Xiang S (2019) Fast and effective copy-move detection of digital audio based on auto segment. International Journal of Digital Crime and Forensics (IJDCF) 11(2):47–62CrossRefGoogle Scholar
  19. 19.
    Javaran TA, Hassanpour H, Abolghasemi V (2015) Automatic estimation and segmentation of partial blur in natural images. Visual Comput 33:1–11Google Scholar
  20. 20.
    Kitahara I, Kogure K, Hagita N (2004) Stealth vision for protecting privacy. In: International conference on pattern recognition, vol 4, pp 404–407Google Scholar
  21. 21.
    Li J, Lu W (2016) Blind image motion deblurring with l0-regularized priors. J Vis Commun Image Represent 40:14–23CrossRefGoogle Scholar
  22. 22.
    Li X, Yang B, Zeng T (2011) Efficient reversible watermarking based on adaptive prediction-error expansion and pixel selection. IEEE Trans Image Process 20 (12):3524–3533MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    Li G, Ito Y, Yu X, Nitta N, Babaguchi N (2009) Recoverable privacy protection for video content distribution. Eurasip J Info Sec 2009(1):4Google Scholar
  24. 24.
    Li J, Fan Y, Lu W, Sun W (2016) Keypoint-based copy-move detection scheme by adopting mscrs and improved feature matching. Multimedia Tools and Applications: 1–15Google Scholar
  25. 25.
    Li X, Li B, Yang B, Zeng T (2013) General framework to histogram-shifting-based reversible data hiding. IEEE Trans Image Process 22 (6):2181–2191MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    Li X, Zhang W, Gui X, Yang B (2013) A novel reversible data hiding scheme based on two-dimensional difference-histogram modification. IEEE Trans Inf Foren Sec 8(7):1091–1100CrossRefGoogle Scholar
  27. 27.
    Liao X, Li K, Yin J (2017) Separable data hiding in encrypted image based on compressive sensing and discrete fourier transform. Multimedia Tools and Applications 76(20):20739–20753CrossRefGoogle Scholar
  28. 28.
    Liao X, Qin Z, Ding L (2017) Data embedding in digital images using critical functions. Signal Process Image Commun 58:146–156CrossRefGoogle Scholar
  29. 29.
    Liao X, Guo S, Yin J, Wang H, Li X, Sangaiah AK (2018) New cubic reference table based image steganography. Multimedia Tools and Applications: 1–18Google Scholar
  30. 30.
    Lin C, Lu W, Huang X, Liu K, Sun W, Lin H, Tan Z (2018) Copy-move forgery detection using combined features and transitive matching. Multimedia Tools and Applications: 1–16Google Scholar
  31. 31.
    Lin C, Lu W, Sun W, Zeng J, Xu T, Lai JH (2018) Region duplication detection based on image segmentation and keypoint contexts. Multimedia Tools and Applications: 1–18Google Scholar
  32. 32.
    Lin C, Lu W, Huang X, Liu K, Sun W, Lin H (2019) Region duplication detection based on hybrid feature and evaluative clustering. Multimedia Tools and Applications: 1–25Google Scholar
  33. 33.
    Lin WS, Tjoa SK, Zhao HV, Liu KJR (2009) Digital image source coder forensics via intrinsic fingerprints. IEEE Trans Inf Foren Sec 4(3):460–475CrossRefGoogle Scholar
  34. 34.
    Liu Z, Lu W (2017) Fast copy-move detection of digital audio. In: 2017 IEEE Second international conference on data science in cyberspace (DSC). IEEE, pp 625–629Google Scholar
  35. 35.
    Liu X, Lu W, Huang T, Liu H, Xue Y, Yeung Y (2018) Scaling factor estimation on jpeg compressed images by cyclostationarity analysis. Multimedia Tools and Applications: 1–18Google Scholar
  36. 36.
    Liu J, Lu W, Weng J, Mao Y, Li G (2018) Double jpeg compression detection based on block statistics. Multimedia Tools and Applications 77(2):1–16Google Scholar
  37. 37.
    Liu X, Lu W, Liu W, Luo S, Liang Y, Li M (2019) Image deblocking detection based on a convolutional neural network. IEEE Access 7:26432–26439CrossRefGoogle Scholar
  38. 38.
    Liu J, Lu W, Zhan Y, Chen J, Xu Z, Li R (2019) Efficient binary image steganalysis based on ensemble neural network of multi-module. J Real-Time Image Process.
  39. 39.
    Liu X, Lu W, Zhang Q, Huang J, Shi YQ (2019) Downscaling factor estimation on pre-jpeg compressed images. IEEE Trans Circuits Syst Video Technol PP(99):1–1Google Scholar
  40. 40.
    Lu W, He L, Yeung Y, Xue Y, Liu H, Feng B (2018) Secure binary image steganography based on fused distortion measurement. IEEE Trans Circuits Syst Video Technol: 1–1. CrossRefGoogle Scholar
  41. 41.
    Lu W, Li R, Zeng L, Chen J, Huang J, Shi YQ (2019) Binary image steganalysis based on histogram of structuring elements. IEEE Trans Circuits Syst Video Technol: 1–1.
  42. 42.
    Lu W, Xue Y, Yeung Y, Liu H, Huang J, Shi YQ (2019) Secure halftone image steganography based on pixel density transition. IEEE Transactions on Dependable and Secure Computing: 1–1.
  43. 43.
    Luo X, Song X, Li X, Zhang W, Lu J, Yang C, Liu F (2016) Steganalysis of hugo steganography based on parameter recognition of syndrome-trellis-codes. Multimedia Tools and Applications 75(21):13557–13583CrossRefGoogle Scholar
  44. 44.
    Ma Y, Luo X, Li X, Bao Z, Zhang Y (2019) Selection of rich model steganalysis features based on decision rough set α -positive region reduction. IEEE Trans Circuits Syst Video Technol 29(2):336–350CrossRefGoogle Scholar
  45. 45.
    Mitskog TF, Ralston RA (2012) Camera blocker for a device with an integrated camera that uses a thin film organic polymer. US Patent App. 13/477,485Google Scholar
  46. 46.
    Muhammad K, Ahmad J, Farman H, Jan Z, Sajjad M, Baik SW (2015) A secure method for color image steganography using gray-level modification and multi-level encryption. TIIS 9(5):1938–1962Google Scholar
  47. 47.
    Muhammad K, Ahmad J, Rehman NU, Jan Z, Sajjad M (2017) Cisska-lsb: color image steganography using stego key-directed adaptive lsb substitution method. Multimedia Tools and Applications 76(6):8597–8626CrossRefGoogle Scholar
  48. 48.
    Muhammad K, Sajjad M, Baik SW (2016) Dual-level security based cyclic18 steganographic method and its application for secure transmission of keyframes during wireless capsule endoscopy. Journal Med Syst 40(5):114CrossRefGoogle Scholar
  49. 49.
    Muhammad K, Sajjad M, Mehmood I, Rho S, Baik SW (2016) A novel magic lsb substitution method (m-lsb-sm) using multi-level encryption and achromatic component of an image. Multimedia Tools and Applications 75(22):14867–14893CrossRefGoogle Scholar
  50. 50.
    Muhammad K, Sajjad M, Mehmood I, Rho S, Baik SW (2018) Image steganography using uncorrelated color space and its application for security of visual contents in online social networks. Futur Gener Comput Syst 86:951–960CrossRefGoogle Scholar
  51. 51.
    Neustaedter C, Greenberg S (2003) The design of a context-aware home media space for balancing privacy and awareness. Proc Ubicomp 2864:297–314Google Scholar
  52. 52.
    Neustaedter C, Greenberg S, Boyle M (2006) Blur filtration fails to preserve privacy for home-based video conferencing. ACM Transactions on Computer-Human Interaction (TOCHI) 13(1):1–36CrossRefGoogle Scholar
  53. 53.
    Ng PL, Ang LM, Seng KP (2010) Privacy preserving stereoscopic vision with one-bit transform. In: IEEE International conference on computer science and information technology, pp 70–74Google Scholar
  54. 54.
    Ou B, Li X, Zhao Y, Ni R, Shi YQ (2013) Pairwise prediction-error expansion for efficient reversible data hiding. IEEE Trans Image Process 22(12):5010–5021MathSciNetzbMATHCrossRefGoogle Scholar
  55. 55.
    Padilla-López J. R., Chaaraoui AA, Flórez-Revuelta F. (2015) Visual privacy protection methods: a survey. Expert Syst Appl 42(9):4177–4195CrossRefGoogle Scholar
  56. 56.
    Peter A, Hartmann T, Muller S, Katzenbeisser S (2013) Privacy-preserving architecture for forensic image recognition. In: IEEE International workshop on information forensics and security, pp 79–84. Tenerife, SpainGoogle Scholar
  57. 57.
    Qian Z, Zhang X, Wang S (2014) Reversible data hiding in encrypted jpeg bitstream. IEEE Transactions on Multimedia 16(5):1486–1491CrossRefGoogle Scholar
  58. 58.
    Qin Z, Yan J, Ren K, Chen CW, Wang C (2014) Towards efficient privacy-preserving image feature extraction in cloud computing. In: Proceedings of the 22nd ACM international conference on multimedia, pp 497–506. New York, USAGoogle Scholar
  59. 59.
    Ran X, Farvardin N (1995) A perceptually motivated three-component image model-part i: description of the model. IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society 4(4):401–15CrossRefGoogle Scholar
  60. 60.
  61. 61.
    Ren Z, Jae Lee Y, Ryoo MS (2018) Learning to anonymize faces for privacy preserving action detection. In: Proceedings of the european conference on computer vision (ECCV), pp 620–636CrossRefGoogle Scholar
  62. 62.
    Ryoo MS, Rothrock B, Fleming C, Yang HJ (2017) Privacy-preserving human activity recognition from extreme low resolution. National conference on artificial intelligence, pp 4255–4262Google Scholar
  63. 63.
    Sadeghi AR, Schneider T, Wehrenberg I (2009) Efficient privacy-preserving face recognition. In: International conference on information security and cryptology, pp 229–244. Seoul, KoreaCrossRefGoogle Scholar
  64. 64.
    Saghaiannejadesfahani SM, Luo Y, Cheung SS (2013) Privacy protected image denoising with secret shares. In: IEEE International conference on image processing, pp 253-256. Orlando, USAGoogle Scholar
  65. 65.
    Shi J, Xu L, Jia J (2014) Discriminative blur detection features. In: IEEE Conference on computer vision and pattern recognition, pp 2965–2972. Columbus, USAGoogle Scholar
  66. 66.
    Su B, Lu S, Tan CL (2011) Blurred image region detection and classification. In: International conference on multimedea 2011, pp 1397–1400. Scottsdale, USAGoogle Scholar
  67. 67.
    Usage of image file formats for websites. [Online]
  68. 68.
    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13 (4):600CrossRefGoogle Scholar
  69. 69.
    Wang W, Dong J, Tan T (2014) Exploring DCT coefficient quantization effects for local tampering detection. IEEE Trans Inf Foren Sec 9(10):1653–1666CrossRefGoogle Scholar
  70. 70.
    Wang R, Lu W, Liu J, Xiang S, Zhao X, Wang J (2018) Digital image splicing detection based on markov features in QDCT and QWT domain. International Journal of Digital Crime and Forensics (IJDCF) 10(4):90–107CrossRefGoogle Scholar
  71. 71.
    Weng S, Zhao Y, Pan JS, Ni R (2008) Reversible watermarking based on invariability and adjustment on pixel pairs. IEEE Signal Process Lett 15:721–724CrossRefGoogle Scholar
  72. 72.
    Wu Z, Wang Z, Wang Z, Jin H (2018) Towards privacy-preserving visual recognition via adversarial training: a pilot study. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 606–624CrossRefGoogle Scholar
  73. 73.
    Xiao H, Lu W, Li R, Zhong N, Yeung Y, Chen J, Xue F, Sun W (2019) Defocus blur detection based on multiscale svd fusion in gradient domain. J Vis Commun Image Represent 59:52–61CrossRefGoogle Scholar
  74. 74.
    Xie Z, Lu W, Liu X, Xue Y, Yeung Y (2018) Copy-move detection of digital audio based on multi-feature decision. J Info Secu Appl 43:37–46Google Scholar
  75. 75.
    Xue F, Ye Z, Lu W, Liu H, Li B (2017) MSE Period based estimation of first quantization step in double compressed jpeg images. Signal Process Image Commu 57:76–83CrossRefGoogle Scholar
  76. 76.
    Xue Y, Liu W, Lu W, Yeung Y, Liu X, Liu H (2018) Efficient halftone image steganography based on dispersion degree optimization. J Real-Time Image Proc: 1–9Google Scholar
  77. 77.
    Yang F, Li J, Lu W, Weng J (2017) Copy-move forgery detection based on hybrid features. Eng Appl Artif Intell 59:73–83CrossRefGoogle Scholar
  78. 78.
    Yeung Y, Lu W, Xue Y, Huang J, Shi YQ (2019) Secure binary image steganography with distortion measurement based on prediction. IEEE Trans Circuits Syst Video Technol: 1–1.
  79. 79.
    Yi S, Zhou Y (2019) Separable and reversible data hiding in encrypted images using parametric binary tree labeling. IEEE Transactions on Multimedia 21(1):51–64CrossRefGoogle Scholar
  80. 80.
    Yi S, Zhou Y, Hua Z (2018) Reversible data hiding in encrypted images using adaptive block-level prediction-error expansion. Signal Processing-Image Commun 64:78–88CrossRefGoogle Scholar
  81. 81.
    Zhang X, Wang S (2006) Efficient steganographic embedding by exploiting modification direction. IEEE Commun Lett 10(11):781–783CrossRefGoogle Scholar
  82. 82.
    Zhang L, Liu K, Li XY, Feng P, Liu C, Liu Y (2014) Enable portrait privacy protection in photo capturing and sharing. arXiv:1410.6582
  83. 83.
    Zhang F, Lu W, Liu H, Xue F (2018) Natural image deblurring based on L0-regularization and kernel shape optimization. Multimedia Tools and Applications 2 (2):1–19Google Scholar
  84. 84.
    Zhang J, Lu W, Yin X, Liu W, Yeung Y (2019) Binary image steganography based on joint distortion measurement. J Vis Commun Image Represent 58:600–605CrossRefGoogle Scholar
  85. 85.
    Zhang Q, Lu W, Jian W (2016) Joint image splicing detection in dct and contourlet transform domain. J Vis Commun Image Represent 40:449–458CrossRefGoogle Scholar
  86. 86.
    Zhang Q, Lu W, Wang R, Li G (2018) Digital image splicing detection based on Markov features in block dwt domain. Multimedia Tools and Applications 77 (3):1–22Google Scholar
  87. 87.
    Zhang C, Rui Y, He LW (2006) Light weight background blurring for video conferencing applications. In: IEEE International conference on image processing, pp 481–484Google Scholar
  88. 88.
    Zhang X, Wang S, Qian Z, Feng G (2011) Reference sharing mechanism for watermark self-embedding. IEEE Trans Image Process 20(2):485–495MathSciNetzbMATHCrossRefGoogle Scholar
  89. 89.
    Zhang Y, Qin C, Zhang W, Liu F, Luo X (2018) On the fault-tolerant performance for a class of robust image steganography. Signal Process 146:99–111CrossRefGoogle Scholar
  90. 90.
    Zheng P, Huang J (2013) Discrete wavelet transform and data expansion reduction in homomorphic encrypted domain. IEEE Trans Image Process 22(6):2455–68MathSciNetzbMATHCrossRefGoogle Scholar
  91. 91.
    Zhou Y, Cao W, Chen CLP (2014) Image encryption using binary bitplane. Signal Process 100:197–207CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2020

Authors and Affiliations

  • Fei Xue
    • 1
    • 2
    • 3
  • Wei Lu
    • 1
    • 2
    • 3
    Email author
  • Honglin Ren
    • 1
    • 2
    • 3
  • Huimei Xiao
    • 1
    • 2
    • 3
  • Qin Zhang
    • 1
    • 2
    • 3
  • Xianjin Liu
    • 1
    • 2
    • 3
  1. 1.School of Data and Computer ScienceSun Yat-sen UniversityGuangzhouChina
  2. 2.Guangdong Key Laboratory of Information Security TechnologySun Yat-sen UniversityGuangzhouChina
  3. 3.Ministry of Education Key Laboratory of Machine Intelligence and Advanced ComputingSun Yat-sen UniversityGuangzhouChina

Personalised recommendations