Abstract
The problem of protecting datasets from the disclosure of confidential information, while published data remains useful for analysis, has recently gained momentum. To solve this problem, anonymization techniques such as k-anonymity, \(\ell \)-diversity, and t-closeness have been used to generate anonymized datasets for training classifiers. While these techniques provide an effective means to generate anonymized datasets, an understanding of how their application affects the performance of classifiers is currently missing. This knowledge enables the data owner and analyst to select the most appropriate classification algorithm and training parameters in order to guarantee high privacy requirements while minimizing the loss of accuracy. In this study, we perform extensive experiments to verify how the classifiers performance changes when trained on an anonymized dataset compared to the original one, and evaluate the impact of classification algorithms, datasets properties, and anonymization parameters on classifiers’ performance.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
The code used for our experiments is available at https://github.com/minaalishahi/classifiersperformance.
- 3.
References
Aggarwal, C.C.: Data Classification: Algorithms and Applications. Chapman and Hall CRC (2014)
Ayala-Rivera, V., McDonagh, P., Cerqueus, T., Murphy, L.: A systematic comparison and evaluation of k-anonymization algorithms for practitioners. Trans. Data Priv. 7(3), 337–370 (2014)
Brickell, J., Shmatikov, V.: The cost of privacy: destruction of data-mining utility in anonymized data publishing. In: International Conference on Knowledge Discovery and Data Mining, pp. 70–78. ACM (2008)
Ciriani, V., di Vimercati, S.D.C., Foresti, S., Samarati, P.: k-anonymous data mining: a survey. In: Aggarwal, C.C., Yu, P.S. (eds.) Privacy-Preserving Data Mining: Models and Algorithms. ADBS, vol. 34, pp. 105–136. Springer, Boston (2008). https://doi.org/10.1007/978-0-387-70992-5_5
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Friedman, A., Schuster, A., Wolff, R.: k-anonymous decision tree induction. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) PKDD 2006. LNCS (LNAI), vol. 4213, pp. 151–162. Springer, Heidelberg (2006). https://doi.org/10.1007/11871637_18
Gong, M., Xie, Y., Pan, K., Feng, K., Qin, A.: A survey on differentially private machine learning. IEEE Comp. Intell. Mag. 15(2), 49–64 (2020)
Holm, S.: A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6(2), 65–70 (1979)
James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning: With Applications in R. Springer, New York (2014). https://doi.org/10.1007/978-1-4614-7138-7
Khodaparast, F., Sheikhalishahi, M., Haghighi, H., Martinelli, F.: Privacy preserving random decision tree classification over horizontally and vertically partitioned data. In: Conference on Dependable, Autonomic and Secure Computing, pp. 600–607 (2018)
LeFevre, K., DeWitt, D.J., Ramakrishnan, R.: Mondrian multidimensional k-anonymity. In: International Conference on Data Engineering, p. 25 (2006)
Li, N., Li, T., Venkatasubramanian, S.: \(t\)-closeness: privacy beyond \(k\)-anonymity and \(l\)-diversity. In: 23rd International Conference on Data Engineering, pp. 106–115. IEEE (2007)
Li, T., Li, N., Zhang, J., Molloy, I.: Slicing: a new approach for privacy preserving data publishing. IEEE Trans. Knowl. Data Eng. 24(3), 561–574 (2012)
Lopuhaä-Zwakenberg, M., Alishahi, M., Kivits, J., Klarenbeek, J., van der Velde, G.J., Zannone, N.: Comparing classifiers’ performance under differential privacy. In: International Conference on Security and Cryptography (SECRYPT) (2021)
Machanavajjhala, A., Kifer, D., Gehrke, J., Venkitasubramaniam, M.: \(l\)-diversity: privacy beyond \(k\)-anonymity. ACM Trans. Knowl. Discov. Data 1(1), 3-es (2007)
Malle, B., Kieseberg, P., Holzinger, A.: DO NOT DISTURB? Classifier behavior on perturbed datasets. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2017. LNCS, vol. 10410, pp. 155–173. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66808-6_11
Malle, B., Kieseberg, P., Weippl, E., Holzinger, A.: The right to be forgotten: towards machine learning on perturbed knowledge bases. In: Buccafurri, F., Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-ARES 2016. LNCS, vol. 9817, pp. 251–266. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45507-5_17
Martinelli, F., Alishahi, M.S.: Distributed data anonymization. In: Conference on Dependable, Autonomic and Secure Computing (DASC), pp. 580–586 (2019)
McDonald, A.W.E., Afroz, S., Caliskan, A., Stolerman, A., Greenstadt, R.: Use fewer instances of the letter “i’’: toward writing style anonymization. In: Fischer-Hübner, S., Wright, M. (eds.) PETS 2012. LNCS, vol. 7384, pp. 299–318. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31680-7_16
Nergiz, M.E., Gök, M.Z.: Hybrid k-anonymity. Comput. Secur. 44, 51–63 (2014)
Samarati, P.: Protecting respondents’ identities in microdata release. IEEE Trans. Knowl. Data Eng. 13(6), 1010–1027 (2001)
Sheikhalishahi, M., Martinelli, F.: Privacy-utility feature selection as a privacy mechanism in collaborative data classification. In: Enabling Technologies: Infrastructure for Collaborative Enterprises, pp. 244–249 (2017)
Sheikhalishahi, M., Saracino, A., Martinelli, F., Marra, A.L.: Privacy preserving data sharing and analysis for edge-based architectures. Int. J. Inf. Secur. 1(2), 1–23 (2021). https://doi.org/10.1007/s10207-021-00542-x
Sheikhalishahi, M., Zannone, N.: On the comparison of classifiers’ construction over private inputs. In: International Conference on Trust, Security and Privacy in Computing and Communications, pp. 691–698 (2020)
Sweeney, L.: \(k\)-anonymity: a model for protecting privacy. Int. J. Uncertainty Fuzziness Knowl.-Based Syst. 10(05), 557–570 (2002)
Wilcoxon, F.: Individual comparisons by ranking methods. Biom. Bull. 1, 60–83 (1945)
Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning: concept and applications. ACM Trans. Intell. Syst. Technol. 10(2), 1–19 (2019)
Ye, M., Wu, X., Hu, X., Hu, D.: Anonymizing classification data using rough set theory. Knowl.-Based Syst. 43, 82–94 (2013)
Acknowledgement
This work has been supported by H2020 EU funded project SECREDAS [GA #783119].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Tables 5, 6, 7, and 8 report respectively the Holm scores of classifiers with respect to accuracy, precision, recall, and F1-score. The higher scores show better performance results for the associated classification algorithm and associated metric.
Figures 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 and 16 show the classifiers performance trained on anonymized Credit, Absent, and Optic datasets for different values of \(k, \ell \), and t.
Rights and permissions
Copyright information
© 2021 IFIP International Federation for Information Processing
About this paper
Cite this paper
Alishahi, M., Zannone, N. (2021). Not a Free Lunch, But a Cheap One: On Classifiers Performance on Anonymized Datasets. In: Barker, K., Ghazinour, K. (eds) Data and Applications Security and Privacy XXXV. DBSec 2021. Lecture Notes in Computer Science(), vol 12840. Springer, Cham. https://doi.org/10.1007/978-3-030-81242-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-81242-3_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81241-6
Online ISBN: 978-3-030-81242-3
eBook Packages: Computer ScienceComputer Science (R0)