Differential Privacy for Classifier Evaluation
Lists
Only you see this
Abstract
Differential privacy provides powerful guarantees that individuals incur minimal additional risk by including their personal data in a database. Most work in differential privacy has focused on differentially private algorithms that produce models, counts, and histograms. Nevertheless, even with a classification model produced by a differentially private algorithm, directly reporting the classifier's performance on a database has the potential for disclosure. Thus, differentially private computation of evaluation metrics for machine learning is an important research area. We find effective mechanisms for area under the receiver-operating characteristic (ROC) curve and average precision.
BibTeX
@inproceedings{boyd2015differential,
author = {Kendrick Boyd and Eric Lantz and David Page},
title = {{Differential Privacy for Classifier Evaluation}},
booktitle = {AISec@CCS},
year = {2015},
url = {https://openreview.net/forum?id=6S4xMNHIsTa},
}Loading related content...