Skip to main content
SpringerLink
Log in

Fast homomorphic SVM inference on encrypted data

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Kernel methods are popular machine learning methods that provide automated pattern analysis of raw datasets. Of particular interest is Support Vector Machines that are used to solve supervised machine learning problems in many areas such as business, finance and healthcare. Nowadays, complex computations and data analytic tasks can be outsourced to specialized third parties. However, data owners might be reluctant to share their data especially when it includes sensitive information. Therefore, a need for privacy-preserving machine learning applications cannot be overstated. We present FHSVM: a Fast Homomorphic evaluation of non-linear SVM prediction on encrypted data using Fully Homomorphic Encryption. We provide design, implementation and several algorithmic and architectural optimizations such as novel packing strategies and parallel implementation to achieve real-time private prediction. We employed the CKKS FHE scheme to implement FHSVM under 128-bit security level. We evaluated FHSVM on a contemporary real-world large dataset compiled for anti-money laundering tasks in Bitcoin transactions. Empirical analysis demonstrates that homomorphic SVM prediction can be performed in 1.25 s on multi-core CPU platforms. In addition, FHSVM shows zero accuracy loss when compared to the non-privacy-preserving implementation. This shows that FHSVM is both computationally secure and fully utilizes the data.

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
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Cui D, Curry D (2005) Prediction in marketing using the support vector machine. Market Sci 24(4):595–615

    Article  Google Scholar 

  2. Yu H, Chen R, Zhang G (2014) A SVM stock selection model within PCA. Proc Comput Sci 31:406–412

    Article  Google Scholar 

  3. Venkatesan C, Karthigaikumar P, Paul A, Satheeskumaran S, Kumar R (2018) ECG signal preprocessing and SVM classifier-based abnormality detection in remote healthcare applications. IEEE Access 6:9767–9773

    Article  Google Scholar 

  4. Ribeiro M, Grolinger K, Capretz MAM (2015) MLaaS: Machine learning as a service. In: 2015 IEEE 14th international conference on machine learning and applications (ICMLA), pp 896–901. https://doi.org/10.1109/ICMLA.2015.152

  5. Gentry C (2009) Fully homomorphic encryption using ideal lattices. In: STOC ’09. New York, NY, USA: Association for Computing Machinery, pp 169–178. https://doi.org/10.1145/1536414.1536440

  6. Maekawa T, Kawamura A, Kinoshita Y, Kiya H (2018) Privacy-preserving svm computing in the encrypted domain. In: Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC). IEEE, pp 897–902

  7. Chuman T, Kurihara K, Kiya H (2017) Security evaluation for block scrambling-based ETC systems against extended jigsaw puzzle solver attacks. In: 2017 IEEE international conference on multimedia and expo (ICME), pp 229–234. https://doi.org/10.1109/ICME.2017.8019487

  8. Rahulamathavan Y, Phan RCW, Veluru S, Cumanan K, Rajarajan M (2014) Privacy-preserving multi-class support vector machine for outsourcing the data classification in cloud. IEEE Trans Dependable Secure Comput 11(5):467–479. https://doi.org/10.1109/TDSC.2013.51

    Article  Google Scholar 

  9. Barnett A, Santokhi J, Simpson M, Smart NP, Stainton-Bygrave C, Vivek S et al (2017) Image classification using non-linear support vector machines on encrypted data. IACR Cryptol ePrint Arch 2017:857

    Google Scholar 

  10. Krizhevsky A, Nair V, Hinton G (2010) Cifar-10 (canadian institute for advanced research), vol 5, no. 4. http://www.cs.toronto.edu/kriz/cifar.html

  11. Brakerski Z, Gentry C, Vaikuntanathan V (2014) (Leveled) fully homomorphic encryption without bootstrapping. ACM Trans Comput Theory 6(3):1–36

    Article  MathSciNet  Google Scholar 

  12. Cheon JH, Kim A, Kim M, Song Y (2017) Homomorphic encryption for arithmetic of approximate numbers. In: Takagi T, Peyrin T (eds) Advances in cryptology – ASIACRYPT 2017. Lecture notes in computer science, vol 10624. Springer, Cham. https://doi.org/10.1007/978-3-319-70694-8_15

    Chapter  Google Scholar 

  13. Park S, Byun J, Lee J, Cheon JH, Lee J (2020) HE-friendly algorithm for privacy-preserving SVM training. IEEE Access 8:57414–57425

    Article  Google Scholar 

  14. Byun J, Lee J, Park S (2021) Privacy-preserving evaluation for support vector clustering. Electron Lett 57(2):61–64

    Article  Google Scholar 

  15. Liu X, Lu R, Ma J, Chen L, Qin B (2016) Privacy-preserving patient-centric clinical decision support system on Naïve Bayesian classification. IEEE J Biomed Health Inform 20(2):655–668. https://doi.org/10.1109/JBHI.2015.2407157

    Article  Google Scholar 

  16. Gong Y, Fang Y, Guo Y (2016) Private data analytics on biomedical sensing data via distributed computation. IEEE/ACM Trans Comput Biol Bioinform 13(3):431–444. https://doi.org/10.1109/TCBB.2016.2515610

    Article  Google Scholar 

  17. Zhu H, Liu X, Lu R, Li H (2017) Efficient and privacy-preserving online medical prediagnosis framework using nonlinear SVM. IEEE J Biomed Health Inform 21(3):838–850. https://doi.org/10.1109/JBHI.2016.2548248

    Article  Google Scholar 

  18. Teo SG, Han S, Lee VC (2013) Privacy preserving support vector machine using non-linear kernels on hadoop mahout. In: 2013 IEEE 16th international conference on computational science and engineering, pp 941–948. https://doi.org/10.1109/CSE.2013.200

  19. Rahulamathavan Y, Phan RCW, Veluru S, Cumanan K, Rajarajan M (2013) Privacy-preserving multi-class support vector machine for outsourcing the data classification in cloud. IEEE Trans Dependable Secure Comput 11(5):467–479

    Article  Google Scholar 

  20. Weber M, Domeniconi G, Chen J, Weidele DKI, Bellei C, Robinson T et al (2019) Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv preprint. arXiv:1908.02591

  21. van Dijk M, Gentry C, Halevi S, Vaikuntanathan V (2010) Fully homomorphic encryption over the integers. In: Gilbert H (ed) Advances in cryptology – EUROCRYPT 2010. Lecture notes in computer science, vol 6110. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13190-5_2

    Chapter  Google Scholar 

  22. Brakerski Z, Vaikuntanathan V (2011) Efficient fully homomorphic encryption from (standard) LWE. SIAM J Comput 43(2):831–871. https://doi.org/10.1137/120868669

    Article  MathSciNet  MATH  Google Scholar 

  23. Brakerski Z, Vaikuntanathan V (2011) Fully homomorphic encryption from ring-LWE and security for key dependent messages. In: Rogaway P (ed) Advances in cryptology – CRYPTO 2011. Lecture notes in computer science, vol 6841. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22792-9_29

    Chapter  Google Scholar 

  24. Brakerski Z (2012) Fully homomorphic encryption without modulus switching from classical GapSVP. In: Cryptology ePrint Archive, Report 078. http://eprint.iacr.org/2012/078. Accessed 1 Mar 2021

  25. López-Alt A, Tromer E, Vaikuntanathan V (2012) On-the-fly multiparty computation on the cloud via multikey fully homomorphic encryption. In: Proceedings of the forty-fourth annual ACM symposium on theory of computing (STOC '12). Association for computing Machinery, New York, USA, pp. 1219–1234. https://doi.org/10.1145/2213977.2214086

    Chapter  Google Scholar 

  26. Fan J, Vercauteren F (2012) Somewhat practical fully homomorphic encryption. In: Cryptology ePrint archive, Report /144. http://eprint.iacr.org/2012/144. Accessed 1 Mar 2021

  27. Gentry C, Sahai A, Waters B (2013) Homomorphic encryption from learning with errors: conceptually-simpler, asymptotically-faster, attribute-based. In: Canetti R, Garay JA (eds) Advances in cryptology – CRYPTO 2013. Lecture notes in computer science, vol 8042. Springer, Berlin, Heidelberg, pp 75–92. https://doi.org/10.1007/978-3-642-40041-4_5

    Chapter  Google Scholar 

  28. Chillotti I, Gama N, Georgieva M, Izabachène M (2016) Faster fully homomorphic encryption: bootstrapping in less than 0.1 seconds. Cryptology ePrint Archive, Report 2016/870. http://eprint.iacr.org/2016/870. Accessed 23 Mar 2021

  29. Cheon JH, Han K, Kim A, Kim M, Song Y (2019) A full RNS variant of approximate homomorphic encryption. In: Cid C, Jacobson M Jr (eds) Selected areas in cryptography – SAC 2018. Lecture notes in computer Science, vol 11349. Springer, Cham, pp 347–368. https://doi.org/10.1007/978-3-030-10970-7_16

    Chapter  Google Scholar 

  30. Potdar K, Pardawala TS, Pai CD (2017) A comparative study of categorical variable encoding techniques for neural network classifiers. Int J Comput Appl 175(4):7–9

    Google Scholar 

  31. Smart NP, Vercauteren F (2014) Fully homomorphic SIMD operations. Des Codes Cryptogr 71(1):57–81

    Article  Google Scholar 

  32. Brutzkus A, Gilad-Bachrach R, Elisha O (2019) Low latency privacy preserving inference. In: Proceedings of the 36th international conference on machine learning. Proceedings of machine learning research, vol 97, pp 812–821. https://proceedings.mlr.press/v97/brutzkus19a.html

  33. Jin C, Badawi AA, Unnikrishnan B, Lin J, Mun CF, Brown JM et al (2019) CareNets: efficient homomorphic CNN for high resolution images. In: NeurIPS workshop on privacy in machine learning. NeurIPS; 2019, pp 1–6. https://oar.a-star.edu.sg/communities-collections/articles/14613. Accessed 25 Mar 2021

  34. Gilad-Bachrach R, Dowlin N, Laine K, Lauter K, Naehrig M, Wernsing J (2016) CryptoNets: applying neural networks to encrypted data with high throughput and accuracy. In: Proceedings of the 33rd international conference on machine learning. Proceedings of machine learning research, vol 48, pp 201–210. https://proceedings.mlr.press/v48/gilad-bachrach16.html

  35. AlBadawi A et al (2020) Towards the alexNet moment for homomorphic encryption: HCNN, the first homomorphic CNN on encrypted data with GPUs. IEEE Trans Emerg Top Comput 9(3):1330–1343. https://doi.org/10.1109/TETC.2020.3014636

    Article  Google Scholar 

  36. Halevi S, Shoup V (2014) Algorithms in helib. In: Annual cryptology conference. Springer, pp 554–571

  37. Albrecht MR, Player R, Scott S (2015) On the concrete hardness of learning with errors. J Math Cryptol 9(3):169–203

    Article  MathSciNet  Google Scholar 

  38. Albrecht MR, Chase M, Chen H, Ding J, Goldwasser S, Gorbunov S et al (2019) Homomorphic encryption standard. IACR Cryptol ePrint Arch 2019:939

    Google Scholar 

  39. Chrono.: C++ Chrono time library. http://en.cppreference.com/w/cpp/chrono. Accessed 2021 Online

  40. Brown T, Kogan A, Lev Y, Luchangco V (2016) Investigating the performance of hardware transactions on a multi-socket machine. In: Proceedings of the 28th ACM symposium on parallelism in algorithms and architectures (SPAA '16). Association for Computing Machinery, New York, NY, USA, pp 121–132. https://doi.org/10.1145/2935764.2935796

    Chapter  Google Scholar 

  41. Bardhan S, Menascé DA (2014) Predicting the effect of memory contention in multi-core computers using analytic performance models. IEEE Trans Comput 64(8):2279–2292

    Article  MathSciNet  Google Scholar 

  42. Boemer F, Cammarota R, Demmler D, Schneider T, Yalame H (2020) MP2ML: a mixed-protocol machine learning framework for private inference. In Proceedings of the 15th international conference on availability, reliability and security (ARES '20). Association for Computing Machinery, New York, NY. https://doi.org/10.1145/3407023.3407045

    Chapter  Google Scholar 

  43. Al Badawi A, Polyakov Y, Aung KMM, Veeravalli B, Rohloff K (2019) Implementation and performance evaluation of RNS variants of the BFV homomorphic encryption scheme. IEEE Trans Emerg Top Comput 9(2):941–956. https://doi.org/10.1109/TETC.2019.2902799

    Article  Google Scholar 

  44. Al Badawi A, Hoang L, Mun CF, Laine K, Aung KMM (2020) Privft: private and fast text classification with homomorphic encryption. IEEE Access 8:226544–226556

    Article  Google Scholar 

Download references

Acknowledgements

Ahmad Al Badawi was supported by Rabdan Academy. Ling Chen and Saru Vig were supported by A*STAR under its RIE2020 Advanced Manufacturing and Engineering (AME) Programmatic Programme (Award A19E3b0099).

Author information

Authors and Affiliations

  1. Homeland Security, Rabdan Academy, Dhafeer St, 114646, Abu Dhabi, UAE

    Ahmad Al Badawi & Saru Vig

  2. Cybersecurity, Institute for Infocomm Research, 1 Fusionopolis Way, Singapore, 138632, Singapore

    Ling Chen

Authors
  1. Ahmad Al Badawi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ling Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Saru Vig
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ahmad Al Badawi.

Ethics declarations

Declarations

The authors have no conflicts of interest to declare that are relevant to the content of this article.

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

Al Badawi, A., Chen, L. & Vig, S. Fast homomorphic SVM inference on encrypted data. Neural Comput & Applic 34, 15555–15573 (2022). https://doi.org/10.1007/s00521-022-07202-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07202-8

Keywords

Search

Navigation