Published July 12, 2025
| Version v2.0.5
Software
Open
PRESTO: Privacy REcommendation and SecuriTy Optimization
Authors/Creators
- 1. Oak Ridge National Laboratory
- 2. National Institute of Standards and Technology
Description
A Python package that provides intelligent recommendations for optimal differential privacy algorithms based on user preferences and dataset characteristics. PRESTO uses Bayesian optimization to automatically determine the best privacy preservation algorithm, privacy loss parameters, confidence intervals, and reliability scores for a given dataset.
Files
ORNL/PRESTO-v2.0.5.zip
Files
(4.8 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:c84fcee2d3c04c927d961ed4bfdf2bd9
|
4.8 MB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/ORNL/PRESTO (URL)
Software
- Repository URL
- https://github.com/ORNL/PRESTO
References
- Dwork, C., & Roth, A. (2014). The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science, 9(3-4), 211-407.
- Abadi, M., et al. (2016). Deep learning with differential privacy. Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 308-318.