• DOI:10.1145/3548606.3560708
• Corpus ID: 250920113

Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It

@article{Casacuberta2022WidespreadUO,
  title={Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It},
  author={S{\'i}lvia Casacuberta and Michael Shoemate and Salil P. Vadhan and Connor Wagaman},
  journal={Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security},
  year={2022}
}

• Sílvia Casacuberta, Michael Shoemate, +1 author Connor Wagaman
• Published 21 July 2022
• Computer Science, Mathematics
• Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security

We identify a new class of vulnerabilities in implementations of differential privacy. Specifically, they arise when computing basic statistics such as sums, thanks to discrepancies between the implemented arithmetic using finite data types (namely, ints or floats) and idealized arithmetic over the reals or integers. These discrepancies cause the sensitivity of the implemented statistics (i.e., how much one individual's data can affect the result) to be much larger than the sensitivity we expect. Consequently, essentially all differential privacy libraries fail to introduce enough noise to hide individual-level information as required by differential privacy, and we show that this may be exploited in realistic attacks on differentially private query systems. In addition to presenting these vulnerabilities, we also provide a number of solutions, which modify or constrain the way in which the sum is implemented in order to recover the idealized or near-idealized bounds on sensitivity.