Borja Balle

TL;DR: This paper presents a general method that recovers and improves prior analyses, yields lower bounds and derives new instances of privacy amplification by subsampling, which leverages a characterization of differential privacy as a divergence which emerged in the program verification community.

TL;DR: In this article, the authors study differential privacy in the context of the recently proposed shuffle model and provide a privacy amplification bound quantifying the level of curator differential privacy achieved by the shuffle model in terms of the local differential privacy.

TL;DR: A hybrid multi-party computation protocol that combines Yao’s garbled circuits with tailored protocols for computing inner products is proposed, suitable for secure computation because it uses an efficient fixed-point representation of real numbers while maintaining accuracy and convergence rates comparable to what can be obtained with a classical solution using floating point numbers.

TL;DR: In this article, an optimal Gaussian mechanism whose variance is calibrated directly using the Gaussian cumulative density function instead of a tail bound approximation is proposed. But the variance formula for the original mechanism is far from tight in the high privacy regime and it cannot be extended to the low privacy regime.

TL;DR: In this paper, the authors provide a tight upper bound on the Renyi Differential Privacy (RDP) (Mironov, 2017) parameters for algorithms that subsample the dataset and then apply a randomized mechanism M to the subsample, in terms of the RDP parameters of M and the subsampling probability parameter.