No Access

Department of Informatics, Systems and Communication, University of Milan-Bicocca, Viale Sarca, 336, Milan, 20126, Italy

and

Alberto Leporati

https://orcid.org/0000-0002-8105-4371

Department of Informatics, Systems and Communication, University of Milan-Bicocca, Viale Sarca, 336, Milan, 20126, Italy

E-mail Address: [email protected]

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0129065724500254Cited by:6 (Source: Crossref)

View article

Abstract

Classifying images has become a straightforward and accessible task, thanks to the advent of Deep Neural Networks. Nevertheless, not much attention is given to the privacy concerns associated with sensitive data contained in images. In this study, we propose a solution to this issue by exploring an intersection between Machine Learning and cryptography. In particular, Fully Homomorphic Encryption (FHE) emerges as a promising solution, as it enables computations to be performed on encrypted data. We therefore propose a Residual Network implementation based on FHE which allows the classification of encrypted images, ensuring that only the user can see the result. We suggest a circuit which reduces the memory requirements by more than $85 %$ compared to the most recent works, while maintaining a high level of accuracy and a short computational time. We implement the circuit using the well-known Cheon–Kim–Kim–Song (CKKS) scheme, which enables approximate encrypted computations. We evaluate the results from three perspectives: memory requirements, computational time and calculations precision. We demonstrate that it is possible to evaluate an encrypted ResNet20 in less than five minutes on a laptop using approximately 15GB of memory, achieving an accuracy of 91.67% on the CIFAR-10 dataset, which is almost equivalent to the accuracy of the plain model (92.60%).

Keywords:

References

1. J. Zhang, L. Zhang, Y. Wang, J. Wang, X. Wei and W. Liu , An efficient multi-objective evolutionary zero-shot neural architecture search framework for image classification, Int. J. Neural Syst. 33(5) (2023) 2350016. Link, Web of Science, Google Scholar
2. Sanaullah, S. Koravuna, U. Rückert and T. Jungeblut , Evaluation of spiking neural nets-based image classification using the runtime simulator RAVSim, Int. J. Neural Syst. 33(9) (2023) 2350044. Link, Web of Science, Google Scholar
3. P. Regulation , Regulation (EU) 2016/679 of the european parliament and of the council, Regulation (EU) 679 (2016) 2016. Google Scholar
4. D. S. Jodas, T. Yojo, S. Brazolin, G. D. N. Velasco and J. A. P. Papa , Detection of trees on street-view images using a convolutional neural network, Int. J. Neural Syst. 32(1) (2022) 2150042. Link, Web of Science, Google Scholar
5. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard and L. D. Jackel , Backpropagation applied to handwritten zip code recognition, Neural Comput. 1(4) (1989) 541–551. Crossref, Web of Science, Google Scholar
6. K. He, X. Zhang, S. Ren and J. Sun , Deep residual learning for image recognition, 2016 IEEE Conf. Computer Vision and Pattern Recognition (CVPR) (IEEE, 2016), pp. 770–778. Crossref, Google Scholar
7. R. L. Rivest, L. Adleman, M. L. Dertouzos et al., On data banks and privacy homomorphisms, Found. Secure Comput. 4(11) (1978) 169–180. Google Scholar
8. R. L. Rivest, A. Shamir and L. Adleman , A method for obtaining digital signatures and public-key cryptosystems, Commun. ACM 21 (1978) 120–126. Crossref, Web of Science, Google Scholar
9. C. Gentry , Fully homomorphic encryption using ideal lattices, in Proc. Forty-First Annual ACM Symp. Theory of Computing, STOC ’09 (ACM, New York, NY, USA, 2009), pp. 169–178. Crossref, Google Scholar
10. I. Chillotti, N. Gama, M. Georgieva and M. Izabachène , TFHE: Fast fully homomorphic encryption over the torus, J. Cryptol. 33 (2020) 34–91. Crossref, Web of Science, Google Scholar
11. L. Ducas and D. Micciancio , FHEW: Bootstrapping homomorphic encryption in less than a second, Advances in Cryptology – EUROCRYPT 2015, eds. E. Oswald and M. Fischlin (Springer, Berlin, Heidelberg, 2015), pp. 617–640. Crossref, Google Scholar
12. J. Fan and F. Vercauteren, Somewhat practical fully homomorphic encryption, Cryptology ePrint Archive, Paper 2012/144 (2012), https://eprint.iacr.org/2012/144. Google Scholar
13. Z. Brakerski, C. Gentry and V. Vaikuntanathan , (Leveled) fully homomorphic encryption without bootstrapping, in Proc. 3rd Innovations in Theoretical Computer Science Conf., ITCS ’12 (ACM, New York, USA, 2012), pp. 309–325. Crossref, Google Scholar
14. J. H. Cheon, A. Kim, M. Kim and Y. Song , Homomorphic encryption for arithmetic of approximate numbers, Advances in Cryptology – ASIACRYPT 2017, eds. T. Takagi and T. Peyrin (Springer International Publishing, Cham, 2017), pp. 409–437. Crossref, Google Scholar
15. R. Gilad-Bachrach, N. Dowlin, K. Laine, K. Lauter, M. Naehrig and J. Wernsing , CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy, in Proc. 33rd Int. Conf. Machine Learning, eds. M. F. Balcan and K. Q. Weinberger , Proceedings of Machine Learning Research, Vol. 48 (ACM, New York, USA, 2016), pp. 201–210. Google Scholar
16. Al Badawi, C. Jin, J. Lin, C. F. Mun, S. J. Jie, B. H. M. Tan, X. Nan, K. M. M. Aung and V. R. Chandrasekhar , Towards the AlexNet moment for homomorphic encryption: HCNN, the first homomorphic CNN on encrypted data with GPUs, IEEE Trans. Emerg. Top. Comput. 9(3) (2021) 1330–1343. Crossref, Web of Science, Google Scholar
17. A. Krizhevsky, G. Hinton et al., Learning multiple layers of features from tiny images, Technical Report (2009), https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf. Google Scholar
18. H. A. Madni, R. M. Umer and G. L. Foresti , Swarm-FHE: Fully homomorphic encryption-based swarm learning for malicious clients, Int. J. Neural Syst. 33(8) (2023) 2350033. Link, Web of Science, Google Scholar
19. J.-P. Bossuat, C. Mouchet, J. Troncoso-Pastoriza and J.-P. Hubaux , Efficient bootstrapping for approximate homomorphic encryption with non-sparse keys, Advances in Cryptology – EUROCRYPT 2021, eds. A. Canteaut and F.-X. Standaert (Springer International Publishing, Cham, 2021), pp. 587–617. Crossref, Google Scholar
20. J.-W. Lee, H. Kang, Y. Lee, W. Choi, J. Eom, M. Deryabin, E. Lee, J. Lee, D. Yoo, Y.-S. Kim and J.-S. No , Privacy-preserving machine learning with fully homomorphic encryption for deep neural network, IEEE Access 10 (2022) 30039–30054. Crossref, Web of Science, Google Scholar
21. E. Lee, J.-W. Lee, J. Lee, Y.-S. Kim, Y. Kim, J.-S. No and W. Choi , Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions, in Proc. 39th Int. Conf. Machine Learning, eds. K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, G. Niu and S. Sabato , Proceedings of the 39 th International Conference on Machine Learning, Baltimore, Maryland, USA, Vol. 162 (PMLR, 2022), pp. 12403–12422. Google Scholar
22. A. Benamira, T. Gurand, T. Peyrin and S. Saha, Tt-tfhe: A torus fully homomorphic encryption-friendly neural network architecture (2023), https://doi.org/10.48550/arXiv.2302.01584. Google Scholar
23. D. Kim and C. Guyot , Optimized privacy-preserving cnn inference with fully homomorphic encryption, Trans. Inf. Foren. Secur. 18 (2023) 2175–2187. Crossref, Web of Science, Google Scholar
24. C. Juvekar, V. Vaikuntanathan and A. Chandrakasan , GAZELLE: A low latency framework for secure neural network inference, 27th USENIX Security Sympos. (ACM, Baltimore, MD, 2018), pp. 1651–1669. Google Scholar
25. L. de Castro, R. Agrawal, R. Yazicigil, A. Chandrakasan, V. Vaikuntanathan, C. Juvekar and A. Joshi, Does fully homomorphic encryption need compute acceleration? (2021), https://doi.org/10.48550/arXiv.2112.06396. Google Scholar
26. J. Lee, E. Lee, Y.-S. Kim, Y. Lee, J.-W. Lee, Y. Kim and J.-S. No, Optimizing layerwise polynomial approximation for efficient private inference on fully homomorphic encryption: A dynamic programming approach (2023), https://doi.org/10.48550/arXiv.2310.10349. Google Scholar
27. E. Lee, J.-W. Lee, J.-S. No and Y.-S. Kim , Minimax approximation of sign function by composite polynomial for homomorphic comparison, IEEE Trans. Depend. Secure Comput. 19(6) (2022) 3711–3727. Crossref, Web of Science, Google Scholar
28. J. H. Cheon, K. Han, A. Kim, M. Kim and Y. Song , A full RNS variant of approximate homomorphic encryption, Sel. Areas Cryptogr. 11349 (2019) 347–368. Google Scholar
29. O. Regev , On lattices, learning with errors, random linear codes, and cryptography, in Proc. Thirty-Seventh Annual ACM Sympos. Theory of Computing, STOC ’05 (ACM, New York, USA, 2005), pp. 84–93. Crossref, Google Scholar
30. V. Lyubashevsky, C. Peikert and O. Regev , On ideal lattices and learning with errors over rings, Advances in Cryptology – EUROCRYPT 2010, ed. H. Gilbert (Springer, Berlin, Heidelberg, 2010), pp. 1–23. Crossref, Google Scholar
31. A. Al Badawi, J. Bates, F. Bergamaschi, D. B. Cousins, S. Erabelli, N. Genise, S. Halevi, H. Hunt, A. Kim, Y. Lee, Z. Liu, D. Micciancio, I. Quah, Y. Polyakov, S. R. V. , K. Rohloff, J. Saylor, D. Suponitsky, M. Triplett, V. Vaikuntanathan and V. Zucca , OpenFHE: Open-source fully homomorphic encryption library, in Proc. 10th Workshop on Encrypted Computing & Applied Homomorphic Cryptography, WAHC’22 (ACM, New York, USA, 2022), pp. 53–63. Crossref, Google Scholar
32. S. Halevi and V. Shoup , Algorithms in HElib, Advances in Cryptology – CRYPTO 2014, eds. J. A. Garay and R. Gennaro (Springer, Berlin, Heidelberg, Berlin, Heidelberg, 2014), pp. 554–571. Crossref, Google Scholar
33. A. A. Badawi and Y. Polyakov, Demystifying bootstrapping in fully homomorphic encryption Cryptology ePrint Archive, Paper 2023/149 (2023), https://eprint.iacr.org/2023/149. Google Scholar
34. K. Han and D. Ki , Better bootstrapping for approximate homomorphic encryption, Topics in Cryptology – CT-RSA 2020, ed. S. Jarecki (Springer International Publishing, Cham, 2020), pp. 364–390. Crossref, Google Scholar
35. A. Kim, Y. Polyakov and V. Zucca , Revisiting homomorphic encryption schemes for finite fields, Advances in Cryptology – ASIACRYPT 2021, eds. M. Tibouchi and H. Wang (Springer International Publishing, Cham, 2021), pp. 608–639. Crossref, Google Scholar
36. L. N. Trefethen , Approximation Theory and Approximation Practice, Extended Edition (SIAM, Philadelphia, PA, 2019). Crossref, Google Scholar
37. M. Albrecht, M. Chase, H. Chen, J. Ding, S. Goldwasser, S. Gorbunov, S. Halevi, J. Hoffstein, K. Laine, K. Lauter, S. Lokam, D. Micciancio, D. Moody, T. Morrison, A. Sahai and V. Vaikuntanathan, Homomorphic encryption security standard, Technical Report, https://HomomorphicEncryption.org, Toronto, Canada (2018). Google Scholar
38. Lattigo v5 Online: EPFL-LDS, Tune Insight SA (2023), https://github.com/tuneinsight/lattigo. Google Scholar
39. B. S. Latibari, K. I. Gubbi, H. Homayoun and A. Sasan , A survey on FHE acceleration, 2023 IEEE 16th Dallas Circuits and Systems Conf. (DCAS) (IEEE, 2023), pp. 1–6. Crossref, Google Scholar
40. N. Samardzic, A. Feldmann, A. Krastev, N. Manohar, N. Genise, S. Devadas, K. Eldefrawy, C. Peikert and D. Sanchez , CraterLake: A hardware accelerator for efficient unbounded computation on encrypted data, in Proc. 49th Annual Int. Sympos. Computer Architecture, ISCA’22 (ACM, New York, USA, 2022), pp. 173–187. Crossref, Google Scholar