Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy Libraries
This work addresses the problem of selecting and improving differential privacy tools for practitioners, library designers, and researchers, though it is incremental as it focuses on benchmarking existing libraries.
The paper benchmarks five differential privacy libraries (Google DP, SmartNoise, diffprivlib, diffpriv, and Chorus) on utility and scalability across four analytics queries, finding they provide similar utility except in some scenarios, with no single library excelling in all areas.
An increasing number of open-source libraries promise to bring differential privacy to practice, even for non-experts. This paper studies five libraries that offer differentially private analytics: Google DP, SmartNoise, diffprivlib, diffpriv, and Chorus. We compare these libraries qualitatively (capabilities, features, and maturity) and quantitatively (utility and scalability) across four analytics queries (count, sum, mean, and variance) executed on synthetic and real-world datasets. We conclude that these libraries provide similar utility (except in some notable scenarios). However, there are significant differences in the features provided, and we find that no single library excels in all areas. Based on our results, we provide guidance for practitioners to help in choosing a suitable library, guidance for library designers to enhance their software, and guidance for researchers on open challenges in differential privacy tools for non-experts.