Privacy-Preserving in Machine Learning: Differential Privacy Case Study

10th International Scientific Conference Technics, Informatics and Education – TIE 2024, str. 89-96

АУТОР(И) / AUTHOR(S): Aleksa Iričanin , Olga Ristić , Marjan Milošević 

Download Full Pdf  

DOI: 10.46793/TIE24.089I

САЖЕТАК /ABSTRACT:

The burgeoning field of Machine Learning (ML) has revolutionized various aspects of our lives. However, the reliance on vast amounts of data, often containing personal information, raises concerns about individual privacy. Striking a balance between effective ML model training and protecting sensitive data is crucial for responsible development and ethical implementation. This paper explores the challenges and potential solutions for preserving privacy in ML training, focusing on differential privacy (DP). The advantages of implementing DP in ML training include robust protection of individual data, enabling meaningful insights from large datasets while maintaining privacy. This is essential for ethical and responsible data usage in machine learning applications. However, DP in ML training presents challenges including scalability issues and trade-offs between utility and privacy. The paper also covers the mathematical mechanisms of Laplace and Gaussian and their noise addition, followed by a comparative analysis of their efficiency within the dataset.

КЉУЧНЕ РЕЧИ / KEYWORDS: 

ML; Differential privacy; Gaussian Mechanism; Laplace Mechanism; data privacy

PROJEKAT / ACKNOWLEDGEMENTS:

This study was supported by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia, and these results are parts of Grant No. 451-03-66 / 2024-03 / 200132 with the University of Kragujevac – Faculty of Technical Sciences Čačak.

ЛИТЕРАТУРА / REFERENCES:

  1. Morris Chang, J., Zhuang, D. & Dumindu Samaraweera, G. (2022). Privacy-Preserving Machine Learning. New York.
  2. Rao Aravilli, S. (2024). Privacy-Preserving Machine Learning, Packt Publishing, UK.
  3. Huang, T. & Zheng, S. (2023). Using Differential Privacy to Define Personal, Anonymous and Pseudonymous Data, IEEE Access, 11, 12. https://doi.org/10.1109/2023.3321578
  4. El Mestari, S. Z., Lenzini, G., Demirci, H. (2024). Preserving data privacy in machine learning systems, Computers & Security, 137, https://doi.org/10.1016/j.cose.2023.103605
  5. Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H., Raad, A. (2023). Reviewing Federated Learning Aggregation Algorithms; Strategies, Contributions, Limitations and Future Perspectives. Electronics, 12, 2287. https://doi.org/10.3390/electronics12102287
  6. Majeed, A. & Lee, S.(2021). Anonymization Techniques for Privacy Preserving Data Publishing: A Comprehensive Survey, IEEE Acces, 9, 8512-8545. https://doi.org/ 10.1109/ACCESS.2020.3045700
  7. Li, D., Wang, J., Tan, Z., Li, X., & Hu, Y. (2020). Differential Privacy Preservation in Interpretable Feedforward – Designed Convolutional Neural Networks. 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom). https://doi.org/1109/trustcom50675.2020.00089
  8. Huang, T. & Zheng, (2023). Using Differential Privacy to Define Personal, Anonymous and Pseudonymous Data, IEEE Access, 11, https://doi.org/10.1109/ACCESS.2023.3321578
  9. Iqbal, M., Tariq, A. , Adnan, M. Ud Din, I.  & Qayyum, T. (2023). FL-ODP: An Optimized Differential Privacy Enabled Privacy Preserving Federated Learning, IEEE Access, 11, 116674-116683.  https://doi.org/10.1109/ACCESS.2023.3325396.
  10. Song, H., Shen, H. Zhao, N., He, Z., Xiong, W., Wu, , Zhang, M.(2024). Adaptive personalized privacy-preserving data collection scheme with local differential privacy, Journal of King Saud University – Computer and Information Sciences, 36(4), 102042. https://doi.org/10.1016/j.jksuci.2024.102042