![](bg8.png)
9 FUTURE WORK
9.1 Datasets Scalability
Exploring the model’s capacity to handle bigger
datasets without performance problems is one direc-
tion for the future. Techniques like parallel process-
ing, distributed computing, and effective data storage
and retrieval methods can be used to accomplish this.
9.2 Convolutional Neural Network
Scalability
Prediction accuracy can be improved by altering the
convolutional neural network model’s design or pa-
rameters. The convolutional neural network model
can also be modified to handle datasets other than im-
age datasets, such as audio and text datasets, by alter-
ing the architecture or preprocessing approaches.
REFERENCES
Cheon, J. H., Kim, A., Kim, M., and Song, Y. (2017). Ho-
momorphic encryption for arithmetic of approximate
numbers. In Takagi, T. and Peyrin, T., editors, Ad-
vances in Cryptology – ASIACRYPT 2017, pages 409–
437, Cham. Springer International Publishing.
Chou, E. J., Gururajan, A., Laine, K., Goel, N. K., Bertiger,
A., and Stokes, J. W. (2020). Privacy-preserving
phishing web page classification via fully homomor-
phic encryption. In ICASSP 2020 - 2020 IEEE Inter-
national Conference on Acoustics, Speech and Signal
Processing (ICASSP), pages 2792–2796.
Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A.,
Yamamoto, K., and Ha, D. (2018). Deep learning for
classical japanese literature.
Deng, L. (2012). The mnist database of handwritten digit
images for machine learning research. IEEE Signal
Processing Magazine, 29(6):141–142.
Hesamifard, E., Takabi, H., and Ghasemi, M. (2017). Cryp-
todl: Deep neural networks over encrypted data.
Hesamifard, E., Takabi, H., and Ghasemi, M. (2019). Deep
neural networks classification over encrypted data. In
Proceedings of the Ninth ACM Conference on Data
and Application Security and Privacy, CODASPY
’19, page 97–108, New York, NY, USA. Association
for Computing Machinery.
Ishiyama, T., Suzuki, T., and Yamana, H. (2020). Highly
accurate cnn inference using approximate activation
functions over homomorphic encryption.
Izabach
`
ene, M., Sirdey, R., and Zuber, M. (2019). Prac-
tical fully homomorphic encryption for fully masked
neural networks. In Mu, Y., Deng, R. H., and Huang,
X., editors, Cryptology and Network Security, pages
24–36, Cham. Springer International Publishing.
Jiang, X., Kim, M., Lauter, K., and Song, Y. (2018). Se-
cure outsourced matrix computation and application
to neural networks. In Proceedings of the 2018 ACM
SIGSAC Conference on Computer and Communica-
tions Security, CCS ’18, page 1209–1222, New York,
NY, USA. Association for Computing Machinery.
Kim, S., Omori, M., Hayashi, T., Omori, T., Wang, L., and
Ozawa, S. (2018). Privacy-Preserving Naive Bayes
Classification Using Fully Homomorphic Encryption:
25th International Conference, ICONIP 2018, Siem
Reap, Cambodia, December 13-16, 2018, Proceed-
ings, Part IV, pages 349–358.
Lou, Q. and Jiang, L. (2021). HEMET: A homomorphic-
encryption-friendly privacy-preserving mobile neural
network architecture. CoRR, abs/2106.00038.
Muhammad, K., Sugeng, K. A., and Murfi, H. (2018).
Machine learning with partially homomorphic en-
crypted data. Journal of Physics: Conference Series,
1108(1):012112.
Sun, X., Zhang, P., Liu, J. K., Yu, J., and Xie, W. (2020).
Private machine learning classification based on fully
homomorphic encryption. IEEE Transactions on
Emerging Topics in Computing, 8(2):352–364.
Vizitiu, A., Nit¸
˘
a, C. I., Puiu, A., Suciu, C., and Itu, L. M.
(2019). Towards privacy-preserving deep learning
based medical imaging applications. In 2019 IEEE
International Symposium on Medical Measurements
and Applications (MeMeA), pages 1–6.
Wang, Y., Liang, X., Hei, X., Ji, W., and Zhu, L. (2021).
Deep learning data privacy protection based on homo-
morphic encryption in aiot. Mobile Information Sys-
tems, 2021:1–11.
Wood, A., Najarian, K., and Kahrobaei, D. (2020). Homo-
morphic encryption for machine learning in medicine
and bioinformatics. 53(4).
Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-
mnist: a novel image dataset for benchmarking ma-
chine learning algorithms.
Xu, R., Joshi, J. B. D., and Li, C. (2019). Cryptonn:
Training neural networks over encrypted data. CoRR,
abs/1904.07303.
DATA 2023 - 12th International Conference on Data Science, Technology and Applications
374