Skip to main content
SpringerLink
Log in

Cloud-based differentially private image classification

  • Published:
Wireless Networks Aims and scope Submit manuscript

Abstract

In this paper, our aim is to design and develop an anonymous full-duplex image classification framework under Differential Privacy. We work under the assumption that both, the cloud and the querier are semi-trusted entities, thus their data should remain safe and confidential. That is, neither the querier nor the cloud should be able to link a particular individual from the other party to an image while maintaining, to a certain extent, suitable classification accuracy. We use Principal Component Analysis (PCA) to transform sample images into anonymized vectors; differentially private synopsis of PCA vectors, and we ensure that the individuals in these vectors remain unidentifiable.

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

Similar content being viewed by others

References

  1. Anava, O., & Levy, K. (2016). k*-nearest neighbors: From global to local. In Advances in neural information processing systems (pp. 4916–4924).

  2. Ascher, U. M., & Greif, C. (2011). A first course on numerical methods (Vol. 7). Philadelphia: SIAM.

    Book  MATH  Google Scholar 

  3. Blum, A., Dwork, C., McSherry, F., & Nissim, K. (2005). Practical privacy: The SULQ framework. In Proceedings of the twenty-fourth ACM SIGMOD-SIGACT-SIGART symposium on principles of database systems (pp. 128–138). ACM.

  4. Chaudhuri, K., Sarwate, A., & Sinha, K. (2012). Near-optimal differentially private principal components. In Advances in neural information processing systems (pp. 989–997).

  5. Cheong, S., Sang Hoon, O., & Lee, S.-Y. (2004). Support vector machines with binary tree architecture for multi-class classification. Neural Information Processing-Letters and Reviews, 2(3), 47–51.

    Google Scholar 

  6. Dwork, C. (2006). Differential privacy. In 33rd international colloquium on automata, languages and programming, part II (ICALP 2006). Venice, Italy (Vol. 4052, pp. 1–12). Springer.

  7. Gomez-Barrero, M., Maiorana, E., Galbally, J., Campisi, P., & Fierrez, J. (2017). Multi-biometric template protection based on homomorphic encryption. Pattern Recognition, 67, 149–163.

    Article  Google Scholar 

  8. Jain, P. (2012). Security issues and their solution in cloud computing. International Journal of Computing and Business Research, 2229–6166. http://www.researchmanuscripts.com/isociety2012/1.pdf.

  9. Jiang, W., Xie, C., & Zhang, Z. (2016). Wishart mechanism for differentially private principal components analysis. In AAAI (pp. 1730–1736).

  10. Li, F., Shin, R., & Paxson, V. (2015). Exploring privacypreservation in outsourced k-nearest neighbors with multiple dataowners. In Proceedings of the 2015 ACM workshop on cloudcomputing security workshop (pp. 53–64). ACM.

  11. Lyons, M. J., Kamachi, M. G., & Gyoba, J. (1997). Japanese female facial expressions (JAFFE), database of digital images. http://www.kasrl.org/jaffe.html.

  12. Narayanan, A., & Shmatikov, V. (2008). Robust de-anonymization of large sparse datasets. In IEEE symposium on security and privacy, 2008. SP 2008 (pp. 111–125). IEEE.

  13. Nassar, M., Wehbe, N., & Al Bouna, B. (2016). K-NN classification under homomorphic encryption: Application on Alabeled Eigen faces dataset. In 2016 IEEE international conference on computational science and engineering (CSE) and IEEE international conference on embedded and ubiquitous computing (EUC) and 15th international symposium on distributed computing and applications for business engineering (DCABES) (pp. 546–552). IEEE.

  14. Powell, V., & Lehe, L. (2015). Principal component analysis @ONLINE.

  15. Singh, G., Sharma, V., & Singh, U. (2016). Different image encryption techniques-survey and overview. International Journal of Advanced Research in Computer Science and Software Engineering, 6(8). http://www.ijarcsse.com/.

  16. Su, D., Cao, J., Li, N., Bertino, E., & Jin, H. (2016). Differentially private k-means clustering. In Proceedings of the sixth ACM conference on data and application security and privacy (pp. 26–37). ACM.

  17. Taheri, M., Mozaffari, S., & Keshavarzi, P. (2017). Face authentication in encrypted domain based on correlation filters. Multimedia Tools and Applications, 77(13), 17043–17067.

    Article  Google Scholar 

  18. Wu, X., Kumar, V., Quinlan, J. R., Ghosh, J., Yang, Q., Motoda, H., et al. (2008). Top 10 algorithms in data mining. Knowledge andinformation systems, 14(1), 1–37.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by CNRS-L and Univ. Pau & Pays Adour, E2S-UPPA/LIUPPA.

Author information

Authors and Affiliations

  1. TICKET Laboratory, Antonine University, Hadat-Baabda, Lebanon

    Elie Chicha & Bechara Al Bouna

  2. LIUPPA Laboratory, University of Pau and Pays Adour, Anglet, France

    Elie Chicha & Richard Chbeir

  3. Computer Science Department, American University of Beirut, Beirut, Lebanon

    Mohamed Nassar

Authors
  1. Elie Chicha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bechara Al Bouna
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohamed Nassar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Richard Chbeir
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Elie Chicha.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chicha, E., Al Bouna, B., Nassar, M. et al. Cloud-based differentially private image classification. Wireless Netw 29, 997–1004 (2023). https://doi.org/10.1007/s11276-018-1885-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11276-018-1885-y

Keywords

Search

Navigation