Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Masked image: Visually protected image dataset privacy-preserving scheme for convolutional neural networks

  • Published:
Peer-to-Peer Networking and Applications Aims and scope Submit manuscript

Abstract

With the widespread use of the internet and advancements in computing and data storage technologies, large amounts of data can be collected and analyzed to explore hidden knowledge and patterns in various areas. Among different data types, images have become an increasingly important information carrier, especially in computer vision research. However, the image data often contains valuable sensitive information of users, such as personal identifiers and biometric information. During the transmission process, once adversaries obtain the image data, it may lead to severe consequences. To solve the image data leakage problem, a lot of image privacy-preserving schemes are proposed. Nevertheless, in most existing schemes, the utility of an image will also be broken while ensuring data privacy. Meanwhile, how to balance privacy and utility is always a nerve-wracking challenge in image privacy protection. In this paper, we focus on designing a privacy-preserving scheme that protects the visual content of an image while retaining its availability for convolutional neural networks (CNN) training and prediction. Specifically, we first use the edge detection technique to discover original image features. Then, we carefully design a noise generation method in which the generated noises can guarantee distance-based indistinguishability while minimally affecting image features. Therefore, with the proposed scheme, the visual content of an image can be protected, and it can still be used for CNN training and prediction. Moreover, we empirically evaluate our proposed scheme with various evaluation criteria. The results demonstrate that the visual content of an image is indeed protected while the accuracy of the trained CNN model is available.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Algorithm 1
Algorithm 2
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data availability

No datasets were generated or analysed during the current study.

References

  1. Duggineni S (2023) Impact of controls on data integrity and information systems. Sci Technol 13(2):29–35

    Google Scholar 

  2. Xu Q, Zhu H, Zheng Y, Wang F, Gao L (2024) Practical and Privacy-Preserving Geo-Social-Based POI Recommendation. J Inf Intell 2(2):148–166

    Google Scholar 

  3. Zheng Z, Wang Q, Wang C (2023) Spoofing attacks and anti-spoofing methods for face authentication over smartphones. IEEE Commun Mag 61(12):213–219

    Article  Google Scholar 

  4. Sharma D, Selwal A (2023) A survey on face presentation attack detection mechanisms: hitherto and future perspectives. Multim Syst 29(3):1527–1577

    Article  Google Scholar 

  5. Lü Q, Liao X, Li H, Huang T (2020) A computation-efficient decentralized algorithm for composite constrained optimization. IEEE Trans Signal Inf Process Netw 6:774–789

    MathSciNet  Google Scholar 

  6. Lü Q, Liao X, Xiang T, Li H, Huang T (2021) Privacy masking stochastic subgradient-push algorithm for distributed online optimization. IEEE Trans Cybern 51(6):3224–3237

    Article  Google Scholar 

  7. Ito I, Kiya H (2009) One-time key based phase scrambling for phase-only correlation between visually protected images. EURASIP J Info Sec 2009:1-11

  8. Ferreira B, Rodrigues J, Leitão J, Domingos HJL (2015) 34th IEEE Symposium on Reliable Distributed Systems, SRDS 2015, Montreal, QC, Canada, September 28 - October 1, 2015. IEEE Computer Society, pp 11–20

    Google Scholar 

  9. Zhou J, Liu X, Au OC, Tang YY (2014) Designing an efficient image encryption-then-compression system via prediction error clustering and random permutation. IEEE Trans Inf Forensics Secur 9(1):39–50

    Article  Google Scholar 

  10. Zhang Y, Xu B, Zhou N (2017) A novel image compression-encryption hybrid algorithm based on the analysis sparse representation. Opt Commun 392:223–233

    Article  Google Scholar 

  11. Kurihara K, Imaizumi S, Shiota S, Kiya H (2017) An encryption-then-compression system for lossless image compression standards. IEICE Trans Inf Syst 100–D(1):52–56

    Article  Google Scholar 

  12. Sirichotedumrong W, Kiya H (2019) Grayscale-based block scrambling image encryption using YCBCR color space for encryption-then-compression systems. APSIPA Trans Signal Inf Process 8:e7

    Article  Google Scholar 

  13. Chuman T, Sirichotedumrong W, Kiya H (2019) Encryption-then-compression systems using grayscale-based image encryption for JPEG images. IEEE Trans Inf Forensics Secur 14(6):1515–1525

    Article  Google Scholar 

  14. Itier V, Puteaux P, Puech W (2020) Recompression of JPEG crypto-compressed images without a key. IEEE Trans Circuits Syst Video Technol 30(3):646–660

    Article  Google Scholar 

  15. Kawamura A, Kinoshita Y, Nakachi T, Shiota S, Kiya H (2020) A privacy-preserving machine learning scheme using ETC images. IEICE Trans Fundam Electron Commun Comput Sci 103–A(12):1571–1578

    Article  Google Scholar 

  16. Maekawa T, Kawamura A, Nakachi T, Kiya H (2019) Privacy-preserving support vector machine computing using random unitary transformation. IEICE Trans Fundam Electron Commun Comput Sci 102–A(12):1849–1855

    Article  Google Scholar 

  17. Beugnon S, Puteaux P, Puech W (2019) 2019 IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, September 22–25, 2019. IEEE, pp 679–683

    Google Scholar 

  18. Tanaka M (2018) Learnable image encryption. CoRR abs/1804.00490. 1804.00490

  19. Sirichotedumrong W, Maekawa T, Kinoshita Y, Kiya H (2019) ICIP. IEEE, pp 674–678

    Google Scholar 

  20. Sirichotedumrong W, Kinoshita Y, Kiya H (2019) Pixel-based image encryption without key management for privacy-preserving deep neural networks. IEEE Access 7:177844–177855

    Article  Google Scholar 

  21. Gaata MT, Hantoosh FF (2016) An efficient image encryption technique using chaotic logistic map and RC4 stream cipher. Int J Mod Trends Eng Res 3(9):213–218

    Article  Google Scholar 

  22. Sirichotedumrong W, Kiya H (2020) 28th European Signal Processing Conference, EUSIPCO 2020, Amsterdam, Netherlands, January 18–21, 2021. IEEE, pp 745–749

    Google Scholar 

  23. Liu C, Zhu T, Zhang J, Zhou W (2023) Privacy intelligence: a survey on image privacy in online social networks. ACM Comput Surv 55(8):161:1-161:35

    Article  Google Scholar 

  24. Sheikh HR, Bovik AC, de Veciana G (2005) An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Trans Image Process 14(12):2117–2128

    Article  Google Scholar 

  25. Chamikara MAP, Bertók P, Khalil I, Liu D, Camtepe S (2020) Privacy preserving face recognition utilizing differential privacy. Comput Secur 97:101951

    Article  Google Scholar 

  26. Fan L (2018) Image pixelization with differential privacy. Lecture Notes in Computer Science. Springer, pp 148–162

    Google Scholar 

  27. Fan L (2019) ICME. IEEE, pp 784–789

    Google Scholar 

  28. Senekane M (2019) Differentially private image classification using support vector machine and differential privacy. Mach Learn Knowl Extr 1(1):483–491

    Article  Google Scholar 

  29. Sharma S, Chen K (2018, October). Image disguising for privacy-preserving deep learning. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security (pp. 2291-2293)

  30. Tonge A, Caragea C (2019) Privacy-aware tag recommendation for accurate image privacy prediction. ACM Trans Intell Syst Technol 10(4):40:1-40:28

    Article  Google Scholar 

  31. Yang G, Cao J, Chen Z, Guo J, Li J (2020) Graph-based neural networks for explainable image privacy inference. Pattern Recognit 105:107360

    Article  Google Scholar 

  32. Yu J, Zhang B, Kuang Z, Lin D, Fan J (2017) iPrivacy: image privacy protection by identifying sensitive objects via deep multi-task learning. IEEE Trans Inf Forensics Secur 12(5):1005–1016

    Article  Google Scholar 

  33. Yu J, Xue H, Liu B, Wang Y, Zhu S, Ding M (2021) GAN-based differential private image privacy protection framework for the internet of multimedia things. Sensors 21(1):58

    Article  Google Scholar 

  34. Ito H, Kinoshita Y, AprilPyone M, Kiya H (2021) Image to perturbation: an image transformation network for generating visually protected images for privacy-preserving deep neural networks. IEEE Access 9:64629–64638

    Article  Google Scholar 

Download references

Funding

This work was supported by National Key R&D Program of China (2021YFB3101300, 2021YFB3101303), National Natural Science Foundation of China (61932015, 62302360), Shaanxi Provincial Key Research and Development Program (2023-ZDLGY-35), Natural Science Basic Research Plan in Shaanxi Province of China (2023-JC-QN-0699), and the Science and Technology on Communication Networks Laboratory (HHX23641X003).

Author information

Authors and Affiliations

  1. School of Cyber Engineering, Xidian University, Xinglong Section of Xifeng Road, Xi’an, 710126, Shaanxi, China

    Xiaoyu Kou, Fengwei Wang, Hui Zhu & Yandong Zheng

  2. Science and Technology on Communication Networks Laboratory, Academy for Network & Communications of CETC, Zhongshan West Road, Shijiazhuang, 050081, Hebei, China

    Fengwei Wang & Xiaopeng Yang

  3. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, Jiangsu, China

    Zhe Liu

  4. Zhejiang Laboratory, Hangzhou, 311100, Zhejiang, China

    Zhe Liu

Authors
  1. Xiaoyu Kou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fengwei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hui Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yandong Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaopeng Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhe Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

X.Kou contributed to the algorithm design of the scheme and the scheme implementation and evaluation. H.Zhu contributed to the system/security models design of the scheme. F.Wang contributed to the experimental design. Y.Zheng contributed to the security analysis of the scheme. X.Yang contributed to the experimental results analysis in the performance evaluation. Z.Liu contributed to the experimental results analysis in the performance evaluation. X.Kou drafts the manuscript, and other authors revise it. All authors approved the final version of the article as accepted for publication, including references.

Corresponding author

Correspondence to Fengwei Wang.

Ethics declarations

Ethics approval

The manuscript does not include human or animal research.

Consent to publish

The manuscript has been submitted solely to this journal and is not published, in press, or submitted elsewhere.

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

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

This article is part of the Topical Collection: Special Issue on 2 - Track on Security and Privacy

Guest Editor: Rongxing Lu

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kou, X., Wang, F., Zhu, H. et al. Masked image: Visually protected image dataset privacy-preserving scheme for convolutional neural networks. Peer-to-Peer Netw. Appl. 17, 2523–2537 (2024). https://doi.org/10.1007/s12083-024-01718-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12083-024-01718-7

Keywords

Search

Navigation