A differential privacy preserving algorithm for greedy decision tree
Shudan Yang, Nan Li, Daozhu Sun, Qiming Du, Wenfu Liu · 2021
In recent years, the contradiction between data application and privacy protection has become increasingly prominent, and differential privacy is considered an effective technology to resolve this contradiction. Therefore, we propose a differential privacy protection algorithm for greedy decision trees. Firstly, the privacy budget is allocated according to the structural characteristics of the tree. Secondly, the algorithm meets ϵ-differential privacy by adding Laplacian perturbation to the leaf nodes and exponential mechanism perturbation to the intermediate nodes. Finally, The integration strategy is used to construct random forest to avoid the instability of single tree. Experimental results show that this algorithm achieves a better balance between data availability and invisibility compared with other algorithms.