Evaluation of Open-source Tools for Differential Privacy
This incremental study helps developers and researchers select appropriate differential privacy tools for specific applications by providing a comparative evaluation framework.
This work tackled the lack of comprehensive comparisons of open-source differential privacy tools by evaluating five tools (OpenDP Smartnoise, Google DP, PyTorch Opacus, Tensorflow Privacy, and Diffprivlib) for their ability to balance privacy-utility trade-offs and resource usage, revealing patterns to guide tool selection under different application needs.
Differential privacy (DP) defines privacy protection by promising quantified indistinguishability between individuals that consent to share their privacy-sensitive information and the ones that do not. DP aims to deliver this promise by including well-crafted elements of random noise in the published data and thus there is an inherent trade-off between the degree of privacy protection and the ability to utilize the protected data. Currently, several open-source tools were proposed for DP provision. To the best of our knowledge, there is no comprehensive study for comparing these open-source tools with respect to their ability to balance DP's inherent trade-off as well as the use of system resources. This work proposes an open-source evaluation framework for privacy protection solutions and offers evaluation for OpenDP Smartnoise, Google DP, PyTorch Opacus, Tensorflow Privacy, and Diffprivlib. In addition to studying their ability to balance the above trade-off, we consider discrete and continuous attributes by quantifying their performance under different data sizes. Our results reveal several patterns that developers should have in mind when selecting tools under different application needs and criteria. This evaluation survey can be the basis for an improved selection of open-source DP tools and quicker adaptation of DP.