Skip to main content
Springer Nature Link
Log in

Adaptive privacy-preserving federated learning

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

Abstract

As an emerging training model, federated deep learning has been widely applied in many fields such as speech recognition, image classification and classification of peer-to-peer (P2P) Internet traffics. However, it also entails various security and privacy concerns. In the past years, many researchers have been carried out toward elaborating solutions to alleviate the above challenges via three underlying technologies, i.e., Secure Multi-Party Computation (SMC), Homomorphic Encryption (HE) and Differential Privacy (DP). Compared with SMC and HE, differential privacy is outstanding in terms of efficiency. However, due to the involvement of noise, DP always needs to make a trade-off between security and accuracy. i.e., achieving a strong security requirement has to sacrifice certain accuracy. To seek the optimal balance, we propose APFL, an Adaptive Privacy-preserving Federated Learning framework in this paper. Specifically, in the APFL, we calculate the contribution of each attribute class to the outputs with a layer-wise relevance propagation algorithm. By injecting adaptive noise to data attributes, our APFL significantly reduces the impact of noise on the final results. Moreover, we introduce the Randomized Privacy-preserving Adjustment Technology to further improve the prediction accuracy of the model. We present a formal security analysis to demonstrate the high privacy level of APFL. Besides, extensive experiments show the superior performance of APFL in terms of accuracy, computation and communication overhead.

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
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L (2016) Deep learning with differential privacy. In: Proceedings of ACM CCS, pp 308–318

  2. Aono Y, Hayashi T, Wang L, Moriai S, et al. (2018) Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans Inform Forensics Secur 13(5):1333–1345

    Article  Google Scholar 

  3. Dwork C, Rothblum GN (2016) Concentrated differential privacy. arXiv:1603.01887

  4. Erlingsson Ú, Pihur V, Korolova A (2014) Rappor: randomized aggregatable privacy-preserving ordinal response. In: Proceedings of ACM CCS, pp 1054–1067

  5. Hao M, Li H, Luo X, Xu G, Yang H, Liu S (2019) Efficient and privacy-enhanced federated learning for industrial artificial intelligence. IEEE Trans Indust Inform

  6. Hard A, Rao K, Mathews R, Beaufays F, Augenstein S, Eichner H, Kiddon C, Ramage D (2018) Federated learning for mobile keyboard prediction. arXiv:1811.03604

  7. Jiang Q, Ma J, Yang C, Ma X, Shen J, Chaudhry SA (2017) Efficient end-to-end authentication protocol for wearable health monitoring systems. Comput Electric Eng 63:182–195

    Article  Google Scholar 

  8. Jiang W, Li H, Xu G, Wen M, Dong G, Lin X (2019) Ptas: privacy-preserving thin-client authentication scheme in blockchain-based pki. Future Gen Comput Sys 96:185–195

    Article  Google Scholar 

  9. Li H, Liu D, Dai Y, Luan TH, Yu S (2018) Personalized search over encrypted data with efficient and secure updates in mobile clouds. IEEE Trans Emerg Topics Comput 6(1):97–109

    Article  Google Scholar 

  10. Li H, Yang Y, Dai Y, Yu S, Xiang Y (2017) Achieving secure and efficient dynamic searchable symmetric encryption over medical cloud data. IEEE Trans Cloud Comput. https://doi.org/10.1109/TCC.2017.2769645

  11. Liu X, Zhu H, Lu R, Li H (2018) Efficient privacy-preserving online medical primary diagnosis scheme on naive bayesian classification. Peer-to-Peer Netw Appl 11(2):334–347

    Article  Google Scholar 

  12. Maqueda AI, Loquercio A, Gallego G, García N, Scaramuzza D (2018) Event-based vision meets deep learning on steering prediction for self-driving cars. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5419–5427

  13. Nasr M, Shokri R, Houmansadr A (2018) Comprehensive privacy analysis of deep learning: stand-alone and federated learning under passive and active white-box inference attacks. arXiv:1812.00910

  14. Papernot N, Song S, Mironov I, Raghunathan A, Talwar K, Erlingsson Ú (2018) Scalable private learning with pate. arXiv:1802.08908

  15. Phan N, Wu X, Hu H, Dou D (2017) Adaptive laplace mechanism: differential privacy preservation in deep learning. In: Proceedings of IEEE ICDM, pp 385–394

  16. Ren H, Li H, Dai Y, Yang K, Lin X (2018) Querying in internet of things with privacy preserving: challenges, solutions and opportunities. IEEE Netw 32(6):144–151

    Article  Google Scholar 

  17. Ren H, Li H, Liang X, He S, Dai Y, Zhao L (2016) Privacy-enhanced and multifunctional health data aggregation under differential privacy guarantees. Sensors 16(9):1463

    Article  Google Scholar 

  18. Shokri R, Shmatikov V (2015) Privacy-preserving deep learning. In: Proceedings of ACM CCS, pp 1310–1321

  19. Sivaprasad A, Ghawalkar N, Hodge S, Sanghavi M, Shinde V (2018) Machine learning based traffic classification using statistical analysis. Int J Recent Innov Trends Comput Commun 6(3):187–191

    Google Scholar 

  20. Song C, Ristenpart T, Shmatikov V (2017) Machine learning models that remember too much. In: Proceedings of ACM CCS, pp 587–601

  21. de Vos BD, Berendsen FF, Viergever MA, Sokooti H, Staring M, Išgum I (2019) A deep learning framework for unsupervised affine and deformable image registration. Medical Image Anal 52:128–143

    Article  Google Scholar 

  22. Wang H, Dong X, Cao Z (2019) Secure and efficient encrypted keyword search for multi-user setting in cloud computing. Peer-to-Peer Netw Appl 12(1):32–42

    Article  Google Scholar 

  23. Xu G, Li H, Dai Y, Yang K, Lin X (2019) Enabling efficient and geometric range query with access control over encrypted spatial data. IEEE Trans Inform Forensics Secur 14(4):870–885

    Article  Google Scholar 

  24. Xu G, Li H, Liu S, Wen M, Lu R (2019) Efficient and privacy-preserving truth discovery in mobile crowd sensing systems. IEEE Trans Vehicular Technol 68(4):3854–3865

    Article  Google Scholar 

  25. Xu G, Li H, Liu S, Yang K, Lin X (2020) Verifynet: secure and verifiable federated learning. IEEE Trans Inform Forensics Secur 15(1):911–926

    Article  Google Scholar 

  26. Xu G, Li H, Ren H, Yang K, Deng RH (2019) Data security issues in deep learning: attacks, countermeasures and opportunities. IEEE Commun Magazine 57(11):116–122. https://doi.org/10.1109/MCOM.001.1900091

    Article  Google Scholar 

  27. Yang Y, Niu X, Li L, Peng H, Ren J, Qi H (2018) General theory of security and a study of hacker!-s behavior in big data era. Peer-to-Peer Netw Appl 11(2):210–219

    Article  Google Scholar 

  28. Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. IEEE Comput Intell Magazine 13(3):55–75

    Article  Google Scholar 

  29. Zhang H, Xiao X, Mercaldo F, Ni S, Martinelli F, Sangaiah AK (2019) Classification of ransomware families with machine learning based on n-gram of opcodes. Future Gen Comput Sys 90:211–221

    Article  Google Scholar 

  30. Zhang J, Zhang Z, Xiao X, Yang Y, Winslett M (2012) Functional mechanism: regression analysis under differential privacy. Proceedings of the VLDB Endowment 5(11):1364–1375

    Article  Google Scholar 

  31. Zhang S, Li H, Dai Y, Li J, He M, Lu R (2018) Verifiable outsourcing computation for matrix multiplication with improved efficiency and applicability. IEEE Internet of Things Journal 5(6):5076–5088

    Article  Google Scholar 

  32. Zhang X, Zhao J, Xu C, Li H, Wang H, Zhang Y (2019) Cipppa: conditional identity privacy-preserving public auditing for cloud-based wbans against malicious auditors. IEEE Trans Cloud Comput: 1–1. https://doi.org/10.1109/TCC.2019.2927219

  33. Zhang Y, Xu C, Ni J, Li H, Shen X (2019) Blockchain-assisted public-key encryption with keyword search against keyword guessing attacks for cloud storage. IEEE Trans Cloud Comput: 1–1. https://doi.org/10.1109/TCC.2019.2923222

  34. Zhao C, Zhao S, Zhao M, Chen Z, Gao CZ, Li H, Tan YA (2019) Secure multi-party computation: theory, practice and applications. Inform Sci 476:357–372

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by the National Key R&D Program of China under Grants 2017YFB0802300 and 2017YFB0802000, the National Natural Science Foundation of China under Grants 61802051, 61772121, 61728102, and 61472065, the Peng Cheng Laboratory Project of Guangdong Province PCL2018KP004, the Guangxi Key Laboratory of Cryptography and Information Security under Grant GCIS201804.

Author information

Authors and Affiliations

  1. The School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China

    Xiaoyuan Liu, Hongwei Li & Guowen Xu

  2. Cyberspace Security Research Center, Peng Cheng Laboratory, Shenzhen, China

    Xiaoyuan Liu & Hongwei Li

  3. CETC Big Data Research Institute Co., Ltd., Guiyang, 550022, China

    Guowen Xu

  4. The Faculty of Computer Science, University of New Brunswick, Fredericton, NB, E3B 5A3, Canada

    Rongxing Lu

  5. The Fortinet Technologies (Canada) ULC, Ottawa, ON, Canada

    Miao He

Authors
  1. Xiaoyuan Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Hongwei Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Guowen Xu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Rongxing Lu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Miao He
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Hongwei Li.

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

Liu, X., Li, H., Xu, G. et al. Adaptive privacy-preserving federated learning. Peer-to-Peer Netw. Appl. 13, 2356–2366 (2020). https://doi.org/10.1007/s12083-019-00869-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12083-019-00869-2

Keywords