B
Borja Balle
Researcher at Amazon.com
Publications - 105
Citations - 3202
Borja Balle is an academic researcher from Amazon.com. The author has contributed to research in topics: Differential privacy & Computer science. The author has an hindex of 24, co-authored 94 publications receiving 1951 citations. Previous affiliations of Borja Balle include Université de Montréal & The Turing Institute.
Papers
More filters
Proceedings Article
Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences
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.
Book ChapterDOI
The Privacy Blanket of the Shuffle Model
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.
Journal ArticleDOI
Privacy-Preserving Distributed Linear Regression on High-Dimensional Data
Adrià Gascón,Phillipp Schoppmann,Borja Balle,Mariana Raykova,Jack Doerner,Samee Zahur,David Evans +6 more
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.
Proceedings Article
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
Borja Balle,Yu-Xiang Wang +1 more
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.
Posted Content
Subsampled R\'enyi Differential Privacy and Analytical Moments Accountant
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.