Towards Understanding the Impact of Model Size on Differential Private Classification

no code implementations • 27 Nov 2021 • Yinchen Shen, Zhiguo Wang, Ruoyu Sun, Xiaojing Shen

Then we propose a feature selection method to reduce the size of the model, based on a new metric which trades off the classification accuracy and privacy preserving.

feature selection Privacy Preserving

Larger Model Causes Lower Classification Accuracy Under Differential Privacy: Reason and Solution

no code implementations • 29 Sep 2021 • Yinchen Shen, Zhiguo Wang, Ruoyu Sun, Xiaojing Shen

Differential privacy (DP) is an essential technique for privacy-preserving, which works by adding random noise to the data.

Privacy Preserving