Answers are grounded in this paper and cite their sources.
This paper discusses the protection of personal information in the context of government data opening driven by big data and proposes an extreme gradient boost (XGBoost) decision tree algorithm based on differential privacy to protect the security of private personal information. First, the authors analyze the significance of opening government data with the support of big data and the measures taken to protect personal information under the development of government data. Second, the authors propose, in combination with XGBoost, a differential privacy-protected XGBoost (DP–XGB) algorithm that can efficiently process high-dimensional data in the context of big data and realize high-precision prediction while protecting personal privacy. Finally, the authors verify the algorithm through extensive experiments. The results show that in comparison with other schemes, DP–XGB scores higher in accuracy by 22.96% and 8.87%, with an average of 19.72% and 2.82%. In terms of training time, DP–XGB is also faster than other schemes.
No takes yet. Share an insight, caveat, or question.
Yixing Yang (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: