<ul data-eligibleForWebStory="false"><li>Research investigates the effectiveness of differential privacy in protecting machine learning models from privacy attacks on their training data.</li><li>A reconstruction attack targeting state-of-the-art differential privacy random forests is introduced in the study.</li><li>Experimental results suggest that while differential privacy reduces the success of reconstruction attacks, forests robust to these attacks may have lower predictive performance.</li><li>Practical recommendations for constructing more resilient differential privacy random forests with maintained predictive performance are provided based on the study's findings.</li></ul>

Training Set Reconstruction from Differentially Private Forests: How Effective is DP?

Discover more