An Efficient Solution for Privacy-preserving Naïve Bayes Classification in Fully Distributed Data Model
DOI:
https://doi.org/10.54654/isj.v1i15.840Keywords:
privacy-preserving data mining and machine learning, secure multi-party computation, Naïve Bayes classification, Homomorphic encryption, Data privacyTóm tắt
Abstract—Recently, privacy preservation has become one of the most important problems in data mining and machine learning. In this paper, we propose a novel privacy-preserving Naïve Bayes classifier for the fully distributed data scenario where each record is only kept by a unique owner. Our proposed solution is based on a secure multi-party computation protocol, so that it has the capability to securely protect each data owner’s privacy, as well as accurately guarantee the classification model. Furthermore, our experimental results show that the new solution is efficient enough for practical applications.
Tóm tắt—Gần đây, bảo vệ tính riêng tư đã trở thành một trong những vấn đề quan trọng nhất trong khai phá dữ liệu và học máy. Trong bài báo này, chúng tôi đề xuất một bộ phân lớp Naïve Bayes đảm bảo tính riêng tư mới cho kịch bản dữ liệu phân tán đầy đủ trong đó mỗi bản ghi chỉ được giữ bởi một người sở hữu duy nhất. Giải pháp nhóm tác giả đề xuất được dựa trên tính toán bảo mật nhiều thành viên nên nó có khả năng bảo vệ an toàn sự riêng tư của mỗi người sở hữu dữ liệu cũng như đảm bảo tính chính xác của mô hình phân lớp. Hơn thế nữa, các kết quả thực nghiệm của chúng tôi chỉ ra rằng giải pháp mới đủ hiệu quả trong các ứng dụng thực tế.
Downloads
References
Y. Lindell and B. Pinkas, “Secure Multiparty Computation for Privacy-Preserving Data Mining,” J. Priv. Confidentiality, vol. 1, no. 1, pp. 59–98, 2009, doi: https://doi.org/10.29012/jpc.v1i1.566.
M. Kantarcıoˇglu, J. Vaidya, and C. Clifton, “Privacy Preserving Naive Bayes Classifier for Horizontally Partitioned Data,” presented at the IEEE ICDM workshop on privacy preserving data mining, 1-7, 2003. [Online]. Available: http://www.cis.syr.edu/~wedu/ppdm2003/papers /1.pdf
J. Vaidya, M. Kantarcioglu, and C. Clifton, “Privacy-preserving Naïve Bayes classification,” VLDB J., vol. 17, pp. 879–898, 2008, doi: https://doi.org/10.1007/s00778-006-0041-y.
B. Schneier, Applied Cryptography, 2nd ed. John Wiley & Sons, 1996.
C. Clifton, M. Kantarcioglu, J. Vaidya, X. Lin, and M. Y. Zhu, “Tools for Privacy Preserving Distributed Data Mining,” ACM SIGKDD Explor. Newsl., vol. 4, no. 2, pp. 28–34, 2002, doi: https://doi.org/10.1145/772862.772867.
Z. Yang, S. Zhong, and R. N. Wright, “PrivacyPreserving Classiflcation of Customer Data without Loss of Accuracy,” in Proceedings of the 2005 SIAM International Conference on Data Mining, 2005, pp. 92–102. doi: https://doi.org/10.1137/1.9781611972757.9.
X. Yi and Y. Zhang, “Privacy-preserving Naive Bayes classification on distributed data via semitrusted mixers,” Inf. Syst., vol. 34, pp. 371–380, 2009, doi: https://doi.org/10.1016/j.is.2008.11.001.
M. E. Skarkala, M. Maragoudakis, S. Gritzalis, and L. Mitrou, “PPDM-TAN: A PrivacyPreserving Multi-Party Classifier,” Computation, vol. 9, no. 6, pp. 1–25, 2021, doi: https://doi.org/10.3390/computation9010006.
P. Paillier, “Public-Key Cryptosystems Based on Composite Degree Residuosity Classes,” in International Conference on the Theory and Applications of Cryptographic Techniques, 1999, pp. 223–238. doi: https://doi.org/10.1007/3-540- 48910-X_16.
C. Gentry, “Fully homomorphic encryption using ideal lattices,” in Proceedings of the forty-first annual ACM symposium on Theory of computing, 2009, pp. 169–178. doi: https://doi.org/10.1145/1536414.1536440.
P. Li, J. Li, Z. Huang, C.-Z. Gao, W.-B. Chen, and K. Chen, “Privacy-preserving outsourced classification in cloud computing,” Clust. Comput., vol. 21, pp. 277–286, 2018, doi: https://doi.org/10.1007/s10586-017-0849-9.
M. Huai, L. Huang, W. Yang, L. Li, and M. Qi, “Privacy-preserving Naive Bayes classification,” in International conference on knowledge science, engineering and management, 2015, pp. 627–638. doi: https://doi.org/10.1007/978-3-319- 25159-2_57.
T. Li, J. Li, Z. Liu, P. Li, and C. Jia, “Differentially private Naive Bayes learning over multiple data sources,” Inf. Sci., vol. 444, pp. 89– 104, 2018, doi: https://doi.org/10.1016/j.ins.2018.02.056.
P. Li, T. Li, H. Ye, J. Li, X. Chen, and Y. Xiang, “Privacy-preserving machine learning with multiple data providers,” Future Gener. Comput. Syst., vol. 87, pp. 341–350, 2018, doi: https://doi.org/10.1016/j.future.2018.04.076.
V. Duy Hien, L. The Dung, and H. Tu Bao, “An efficient approach for secure multi-party computation without authenticated channel,” Inf. Sci., vol. 527, pp. 356–368, 2020, doi: https://www.doi.org/10.1016/j.ins.2019.07.031.
O. Goldreich, “Basic Applications,” in Foundations of Cryptography, vol. II, Cambridge University Press, 2004.
F. Hao, P. Y. A. Ryan, and P. Zielin´ski, “Anonymous voting by two-round public discussion,” IET Inf. Secur., vol. 4, no. 2, pp. 62– 67, 2010, doi: https://doi.org/10.1049/ietifs.2008.0127.
H. Hofmann, “Statlog (German Credit Data) Data Set,” 1994. https://archive.ics.uci.edu/ml/datasets/statlog+(g erman+credit+data)
Downloads
Published
How to Cite
Issue
Section
License
Proposed Policy for Journals That Offer Open Access
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Proposed Policy for Journals That Offer Delayed Open Access
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication, with the work [SPECIFY PERIOD OF TIME] after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
