Abstract

The rapid adoption of machine learning across diverse application domains has intensified concerns regarding data privacy. Although numerous privacy-preserving techniques have been proposed, their effectiveness is typically evaluated within isolated domains, which limits the understanding of their generalizability. This paper investigates the domain-dependent behavior of privacy-preserving machine learning through a comprehensive cross-domain empirical study. A hybrid privacy framework is implemented that combines suppression, generalization, and perturbation techniques to protect sensitive information while maintaining data utility. The framework is evaluated across five heterogeneous domains, namely healthcare, finance, social media, cybersecurity, and Internet of Things (IoT) environments, spanning six real-world datasets. The experimental results demonstrate that the effectiveness of privacy-preserving mechanisms varies significantly across domains. Structured and network-based datasets, such as financial and cybersecurity data, maintain high predictive performance under privacy constraints, whereas text-based social data experiences noticeable performance degradation. A complementary trade-off analysis, expressed through utility-retention and a privacy–utility efficiency measure, further quantifies these differences. The findings highlight the limitations of one-size-fits-all privacy solutions and emphasize the need for adaptive, domain-aware privacy strategies in real-world machine learning applications.

References

• Ali, Y. and Ali, L. (2026) ‘A Decision Support Framework for Meal Healthiness: Machine Learning Analysis with Expert Nutritional and Goal-Oriented Interpretation’.
• Shokri, R., Stronati, M., Song, C. and Shmatikov, V. (2017) ‘Membership inference attacks against machine learning models’, IEEE Symposium on Security and Privacy, pp. 3–18.
• Dwork, C. (2008) ‘Differential privacy: A survey of results’, International Conference on Theory and Applications of Models of Computation, pp. 1–19.
• Ali, L., Mathieu, H. and Biennier, F. (2006) ‘Monitoring and managing distributed networks using mobile agents’, Proceedings of the 2nd International Conference on Information and Communication Technologies (ICTTA). IEEE, vol. 2, pp. 3377–3382.
• Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K. and Zhang, L. (2016) ‘Deep learning with differential privacy’, Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308–318.
• Ali, L. (2008) Gestionnaire d’infrastructure distribuée. PhD thesis, Institut National des Sciences Appliquées de Lyon.
• Sweeney, L. (2002) ‘k-anonymity: A model for protecting privacy’, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(5), pp. 557–570.
• Fung, B.C.M., Wang, K., Chen, R. and Yu, P.S. (2010) ‘Privacy-preserving data publishing: A survey of recent developments’, ACM Computing Surveys, 42(4), pp. 1–53.
• Dal Pozzolo, A., Caelen, O., Johnson, R.A. and Bontempi, G. (2015) ‘Calibrating probability with undersampling for unbalanced classification’, IEEE Symposium Series on Computational Intelligence, pp. 159–166.
• Moustafa, N. and Slay, J. (2015) ‘UNSW-NB15: A comprehensive data set for network intrusion detection systems’, Military Communications and Information Systems Conference (MilCIS), pp. 1–6.
• Ali, L., Jaber, M., Chaari, S. and Biennier, F. (2007) ‘Context-aware infrastructure to support distributed industrial services’, Proceedings of the IEEE International Conference on Emerging Technologies and Factory Automation (ETFA). IEEE, pp. 716–719.
• Geyer, R.C., Klein, T. and Nabi, M. (2017) ‘Differentially private federated learning: A client level perspective’, arXiv preprint arXiv:1712.07557.
• Beaulieu-Jones, B.K., Wu, Z.S., Williams, C., Lee, J., Bhavnani, S.P., Byrd, J.B. and Greene, C.S. (2019) ‘Privacy-preserving generative deep neural networks support clinical data sharing’, Circulation: Cardiovascular Quality and Outcomes, 12(7).
• Machanavajjhala, A., Kifer, D., Gehrke, J. and Venkitasubramaniam, M. (2007) ‘l-Diversity: Privacy beyond k-anonymity’, ACM Transactions on Knowledge Discovery from Data, 1(1), pp. 1–52.
• Li, N., Li, T. and Venkatasubramanian, S. (2007) ‘t-Closeness: Privacy beyond k-anonymity and l-diversity’, IEEE International Conference on Data Engineering, pp. 106–115.
• Agrawal, R. and Srikant, R. (2000) ‘Privacy-preserving data mining’, ACM SIGMOD International Conference on Management of Data, pp. 439–450.
• Kargupta, H., Datta, S., Wang, Q. and Sivakumar, K. (2003) ‘On the privacy preserving properties of random data perturbation techniques’, IEEE International Conference on Data Mining, pp. 99–106.
• McMahan, H.B., Moore, E., Ramage, D., Hampson, S. and Arcas, B.A. (2017) ‘Communication-efficient learning of deep networks from decentralized data’, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, pp. 1273–1282.
• Acar, A., Aksu, H., Uluagac, A.S. and Conti, M. (2018) ‘A survey on homomorphic encryption schemes: Theory and implementation’, ACM Computing Surveys, 51(4), pp. 1–35.
• Medford, R.J., Saleh, S.N., Sumarsono, A., Perl, T.M. and Lehmann, C.U. (2020) ‘Anonymization and perturbation methods for healthcare data privacy’, Journal of Biomedical Informatics, 102.
• Ali, L. and Biennier, F. (2005) ‘Integration of security requirements in virtual enterprises’, APMS’05, Washington, United States.
• Alabdulatif, A., Khalil, I. and Yi, X. (2021) ‘Privacy-preserving data publishing: A survey on recent developments’, Journal of Network and Computer Applications, 190.
• Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H.R., Albarqouni, S. and Cardoso, M.J. (2020) ‘The future of digital health with federated learning’, npj Digital Medicine, 3(119).
• Veale, M., Binns, R. and Edwards, L. (2018) ‘Algorithms that remember: Model inversion attacks and data protection law’, Philosophical Transactions of the Royal Society A, 376.
• Dua, D. and Graff, C. (2019) UCI Machine Learning Repository. Available at: http://archive.ics.uci.edu/ml.
• Go, A., Bhayani, R. and Huang, L. (2009) Twitter Sentiment Classification using Distant Supervision. Stanford University.
• Garcia, S., Parmisano, A., Erquiaga, M.J. and Hofstede, R. (2020) The IoT-23 Dataset: A Labeled Dataset with Malicious and Benign IoT Network Traffic. Stratosphere Laboratory. Available at: https://www.stratosphereips.org/datasets-iot23.
• Issa, N., Gruska, D. and Ali, L. (2026) ‘A hybrid GAM-based model for predicting vulnerability exploitation’, in Cappiello, C., Hartig, O., Sellami, M. and Ouni, A. (eds.) Cooperative Information Systems. Lecture Notes in Computer Science, vol. 15535. Cham: Springer.
• Hajrulla, S., Ali, L. and Souliman, N. (2023) ‘Normal distribution on energy saving problems for the wireless sensor network life on the vacation period’, Journal of Natural Sciences & Mathematics (JNSM), 8.
• Farag, K., Ali, L., Mutai, N.C., Luqman, R., Mahmoud, A. and Krasniqi, N. (2025) ‘Machine learning for predicting bank stability: The role of income diversification in European banking’, FinTech, 4(2), 21. Available at: https://doi.org/10.3390/fintech4020021.