Skip to main content

P-SGD: A Stochastic Gradient Descent Solution for Privacy-Preserving During Protection Transitions

  • 1540 Accesses

Part of the Lecture Notes in Computer Science book series (LNISA,volume 12751)


Advances in privacy-enhancing technologies, such as context-aware and personalized privacy models, have paved the way for successful management of the data utility-privacy trade-off. However, significantly lowering the level of data protection when balancing utility-privacy to meet the individual’s needs makes subsequent protected data more precise. This increases the adversary’s ability to reveal the real values of the previous correlated data that needed more protection, making existing privacy models vulnerable to inference attacks. To overcome this problem, we propose in this paper a stochastic gradient descent solution for privacy-preserving during protection transitions, denoted P-SGD. The goal of this solution is to minimize the precision gap between sequential data when downshifting the protection by the privacy model. P-SGD intervenes at the protection descent phase and performs an iterative process that measures data dependencies, and gradually reduces protection accordingly until the desired protection level is reached. It considers also possible changes in protection functions and studies their impact on the protection descent rate. We validated our proposal and evaluated its performance. The results show that P-SGD is fast, scalable, and maintains low computational and storage complexity.


  • Data privacy
  • Data protection transitions
  • Stochastic gradient descent methods
  • Context-awareness
  • Internet of Things

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-79382-1_3
  • Chapter length: 17 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   89.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-79382-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   119.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.
Fig. 11.


  1. 1. (P-SGD Prototype).


  1. Bottou, L., Bousquet, O.: The tradeoffs of large scale learning. Adv. Neural Inf. Process. Syst. 20, 161–168 (2007)

    Google Scholar 

  2. Bou-Chaaya, K., et al.: \(\delta \)-Risk: Toward Context-aware Multi-objective Privacy Management in Connected Environments. ACM Trans. Internet Technol. 21(2), 1–31 (2021)

    Google Scholar 

  3. Cao, J., et al.: Castle: continuously anonymizing data streams. IEEE Trans. Dependable Secure Comput. 8, 337–352 (2010)

    Google Scholar 

  4. Chaaya, K.B., Barhamgi, M., Chbeir, R., Arnould, P., Benslimane, D.: Context-aware system for dynamic privacy risk inference: application to smart IoT environments. Future Gener. Comput. Syst. 101, 1096–1111 (2019)

    CrossRef  Google Scholar 

  5. Chamikara, M., et al.: An efficient and scalable privacy preserving algorithm for big data and data streams. Comput. Secur. 87, 101570 (2019)

    CrossRef  Google Scholar 

  6. Gao, S., Ma, J., Sun, C., Li, X.: Balancing trajectory privacy and data utility using a personalized anonymization model. J. Netw. Comput. Appl. 38, 125–134 (2014)

    CrossRef  Google Scholar 

  7. Gheisari, M., et al.: A context-aware privacy-preserving method for IoT-based smart city using software defined networking. Comput. Secur. 87, 101470 (2019)

    CrossRef  Google Scholar 

  8. Han, S., et al.: Privacy-preserving gradient-descent methods. IEEE Trans. Knowl. Data Eng. 22, 884–899 (2010)

    CrossRef  Google Scholar 

  9. Islam, M.Z., Brankovic, L.: Privacy preserving data mining: a noise addition framework using a novel clustering technique. Knowl.-Based Syst. 24, 1214–1223 (2011)

    CrossRef  Google Scholar 

  10. Komishani, E.G., Abadi, M., Deldar, F.: PPTD: preserving personalized privacy in trajectory data publishing by sensitive attribute generalization and trajectory local suppression. Knowl.-Based Syst. 94, 43–59 (2016)

    CrossRef  Google Scholar 

  11. Li, M., Sun, X., Wang, H., Zhang, Y., Zhang, J.: Privacy-aware access control with trust management in web service. World Wide Web 14, 407–430 (2011).

    CrossRef  Google Scholar 

  12. Machanavajjhala, A., Kifer, D., Gehrke, J., Venkitasubramaniam, M.: l-diversity: privacy beyond k-anonymity. ACM Trans. Knowl. Discov. Data (TKDD) 1(1), 3-es (2007)

    CrossRef  Google Scholar 

  13. de Matos, E., et al.: Providing context-aware security for IoT environments through context sharing feature. In: TrustCom/BigDataSE, pp. 1711–1715. IEEE (2018)

    Google Scholar 

  14. Meng, X., et al.: Towards privacy preserving social recommendation under personalized privacy settings. World Wide Web 22(6), 2853–2881 (2018).

    CrossRef  Google Scholar 

  15. Michael, J., Koschmider, A., Mannhardt, F., Baracaldo, N., Rumpe, B.: User-centered and privacy-driven process mining system design for IoT. In: Cappiello, C., Ruiz, M. (eds.) CAiSE 2019. LNBIP, vol. 350, pp. 194–206. Springer, Cham (2019).

    CrossRef  Google Scholar 

  16. Pingley, A., Yu, W., Zhang, N., Fu, X., Zhao, W.: Cap: a context-aware privacy protection system for location-based services. In: 2009 29th IEEE International Conference on Distributed Computing Systems, pp. 49–57. IEEE (2009)

    Google Scholar 

  17. Qiu, G., et al.: Mobile semantic-aware trajectory for personalized location privacy preservation. IEEE IoT J. (2020).

  18. Shin, H., Kim, S., Shin, J., Xiao, X.: Privacy enhanced matrix factorization for recommendation with local differential privacy. IEEE Trans. Knowl. Data Eng. 30(9), 1770–1782 (2018)

    CrossRef  Google Scholar 

  19. Sweeney, L.: k-anonymity: a model for protecting privacy. Int. J. Uncertainty, Fuzziness Knowl.-Based Syst. 10, 557–570 (2002)

    MathSciNet  CrossRef  Google Scholar 

  20. Sylla, T., Chalouf, M.A., Krief, F., Samaké, K.: Towards a context-aware security and privacy as a service in the internet of things. In: Laurent, M., Giannetsos, T. (eds.) WISTP 2019. LNCS, vol. 12024, pp. 240–252. Springer, Cham (2020).

    CrossRef  Google Scholar 

  21. Vollmer, N.: Table of contents EU General Data Protection Regulation (2018)

    Google Scholar 

  22. Vu, D.H., et al.: An efficient approach for secure multi-party computation without authenticated channel. Inf. Sci. 527, 356–368 (2020)

    MathSciNet  CrossRef  Google Scholar 

  23. Wang, L., Yu, Z., Guo, B., Ku, T., Yi, F.: Moving destination prediction using sparse dataset: a mobility gradient descent approach. ACM Trans. Knowl. Discov. Data (TKDD) 11(3), 1–33 (2017)

    Google Scholar 

  24. Xiong, J., et al.: A personalized privacy protection framework for mobile crowd sensing in IoT. IEEE Trans. Industr. Inf. 16, 4231–4241 (2019)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Karam Bou-Chaaya .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Bou-Chaaya, K., Chbeir, R., Barhamgi, M., Arnould, P., Benslimane, D. (2021). P-SGD: A Stochastic Gradient Descent Solution for Privacy-Preserving During Protection Transitions. In: La Rosa, M., Sadiq, S., Teniente, E. (eds) Advanced Information Systems Engineering. CAiSE 2021. Lecture Notes in Computer Science(), vol 12751. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-79381-4

  • Online ISBN: 978-3-030-79382-1

  • eBook Packages: Computer ScienceComputer Science (R0)