In adaptive data analysis, a mechanism gets n i.i.d. samples from an
unk...
A private learner is trained on a sample of labeled points and generates...
In this work we introduce an interactive variant of joint differential
p...
A dynamic algorithm against an adaptive adversary is required to be corr...
Let π be an efficient two-party protocol that given security parameter
κ...
We provide a lowerbound on the sample complexity of distribution-free pa...
We present a streaming problem for which every adversarially-robust stre...
We are entering a new "data everywhere-anytime" era that pivots us from ...
The shuffle model of differential privacy was proposed as a viable model...
The shuffle model of differential privacy (Erlingsson et al. SODA 2019; ...
Motivated by the desire to bridge the utility gap between local and trus...
We study the problem of verifying differential privacy for loop-free pro...
We study the problem of verifying differential privacy for straight line...
A protocol by Ishai et al. (FOCS 2006) showing how to implement distribu...
In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for
n-p...
In a recent paper Chan et al. [SODA '19] proposed a relaxation of the no...
There is a significant conceptual gap between legal and mathematical thi...
This work studies differential privacy in the context of the recently
pr...
We present a private learner for halfspaces over an arbitrary finite dom...
We briefly report on a linear program reconstruction attack performed on...
While statistics and machine learning offers numerous methods for ensuri...
Data driven segmentation is the powerhouse behind the success of online
...
Data is continuously generated by modern data sources, and a recent chal...
We compare the sample complexity of private learning [Kasiviswanathan et...