Published July 12, 2025 | Version v2.0.5
Software Restricted

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

Restricted

The record is publicly accessible, but files are restricted. <a href="https://zenodo.org/account/settings/login?next=https://zenodo.org/records/15866860">Log in</a> to check if you have access.

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.