Optimization of Privacy Budget Allocation in Differential Privacy Technology: An Empirical Study

Yunfei Liu

doi:10.47297/taposatWSP2633-456906.20240502

PDF
Export
Share
Collection
Album

Optimization of Privacy Budget Allocation in Differential Privacy Technology: An Empirical Study

Volume 5, Issue 2

Views: 0 Downloads: 1

Optimization of Privacy Budget Allocation in Differential Privacy Technology: An Empirical Study
School of Automation, Guangdong University of Technology, Guangzhou Guangdong 510006, China
Vol. 5, Issue 2, Pages: 60-68(2024)
Published： 20 August 2024 ，
DOI：10.47297/taposatWSP2633-456906.20240502
Accepted：

Scan QR Code

Liu Yunfei.Optimization of Privacy Budget Allocation in Differential Privacy Technology: An Empirical Study[J].Theory and Practice of Science and Technology,2024,05(02):60-68.
DOI：

Liu Yunfei.Optimization of Privacy Budget Allocation in Differential Privacy Technology: An Empirical Study[J].Theory and Practice of Science and Technology,2024,05(02):60-68. DOI： 10.47297/taposatWSP2633-456906.20240502.

摘要

Abstract

Differential privacy is a technology to protect personal privacy. It protects sensitive personal information by introducing noise during data processing. In Differential privacy

privacy budget is an important concept

which is used to measure the size of noise introduced in data processing. At present

the widely used method of uniform allocation of privacy budget will easily lead to two problems

namely

data distortion and insufficient protection of data privacy. To solve these problems

this paper adopts a combination of Binary tree and Geometric progression allocation method. This technology is based on the Binary tree structure

the privacy budget is allocated to each node through the rule of Geometric progression to prevent the amount of noise introduced from being too large or too small. All nodes of the binary tree represent the entire data set

and each leaf node represents a single data. Privacy budget should allocate from the root node and is gradually allocated to child nodes based on data processing needs and privacy protection requirements. Each node assigns a privacy budget to its child nodes based on their number of child nodes and the needs of data processing operations. Through Mathematical analysis and experimental evaluation

the effectiveness and feasibility of this method are verified. The experimental results show that the combination of Geometric progression and Binary tree for privacy budget allocation is very flexible

it is better than the method of averagely allocating privacy budgets

which can protect individual privacy while maintaining data availability.

关键词

Keywords

Privacy BudgetBinary TreeGeometric SeriesData Availability

references

Goswami, P., & Madan, S. (2017). Privacy preserving data publishing and data anonymization approaches: A review. In: 2017 International Conference on Computing, Communication and Automation. 139-142.

Shmueli, E., Vaisenberg, R., Elovici, Y., & Glezer, C. (2010). Database encryption: an overview of contemporary challenges and design considerations. ACM SIGMOD Record, 38(3): 29-34.

Lee, J., & Clifton, C. (2011). How much is enough? choosing ε for differential privacy. In: Information Security: 14th International Conference. Xi'an. 325-340.

Li, Q., Wu, Z., Wen, Z., & He, B. (2020). Privacy-preserving gradient boosting decision trees. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1): 784-791.

Tian, F., Zhang, S., Lu, L., Liu, H., & Gui, X. (2017). A novel personalized differential privacy mechanism for trajectory data publication. In: 2017 International Conference on Networking and Network Applications. 61-68.

Wang, Z., Hu, J., Lv, R., Wei, J., Wang, Q., Yang, D., & Qi, H. (2018). Personalized privacy-preserving task allocation for mobile crowdsensing. IEEE Transactions on Mobile Computing, 18(6): 1330-1341.

El Ouadrhiri, A., & Abdelhadi, A. (2022). Differential privacy for deep and federated learning: A survey. IEEE Access, 10: 22359-22380.

Dwork, C. (2006). Differential privacy. In: International Colloquium on Automata, Languages, and Programming. 1-12.

Dwork, C., & Roth, A. (2014). The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science, 9(3–4): 211-407.

Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006). Calibrating noise to sensitivity in private data analysis. In: Theory of Cryptography: Third Theory of Cryptography Conference. New York. 265-284.

Dwork, C., Naor, M., Pitassi, T., & Rothblum, G. N. (2010). Differential privacy under continual observation. Proceedings of the Forty-second ACM Symposium on Theory of Computing, 715-724.

Dwork, C., Rothblum, G. N., & Vadhan, S. (2010). Boosting and differential privacy. In: 2010 IEEE 51st Annual Symposium on Foundations of Computer Science. 51-60.

Dwork, C. (2008). Differential privacy: A survey of results. International Conference on Theory and Applications of Models of Computation, 1-19.

Wang, J., Liu, S., Li, Y., Cao, H., & Liu, M. (2016). Differentially private spatial decompositions for geospatial point data. China Communications, 13(4): 97-107.

Public Health Science Data Center. (2019). Hepatitis. http://www.phsciencedata.cn/Share/index.html?8defcfc2-b9a4-4225-b92c-ebb002321cea.

Alert me when the article has been cited

Submit

No data

Related Author

No data

Related Institution

No data

⁰