Event identification is increasingly recognized as crucial for enhancing...
We introduce a family of information leakage measures called maximal
(α,...
In an effort to address the training instabilities of GANs, we introduce...
There is a growing need for models that are interpretable and have reduc...
We introduce a family of information leakage measures called maximal
α,β...
We consider the problem of learning the structure underlying a Gaussian
...
We introduce a gain function viewpoint of information leakage by proposi...
The electrical power grid is a critical infrastructure, with disruptions...
We introduce a new differential privacy (DP) accountant called the
saddl...
This paper examines model parameter estimation in dynamic power systems ...
Most differential privacy mechanisms are applied (i.e., composed) numero...
Deep Learning (DL) models achieve great successes in many domains. Howev...
We prove a two-way correspondence between the min-max optimization of ge...
Power systems are prone to a variety of events (e.g. line trips and
gene...
We present a variational characterization for the Rényi divergence of
or...
We study the problem of localizing multiple sources of forced oscillatio...
We model and study the problem of localizing a set of sparse forcing inp...
The minimum mean-square error (MMSE) achievable by optimal estimation of...
We consider a problem of guessing, wherein an adversary is interested in...
In today's ML, data can be twisted (changed) in various ways, either for...
We introduce a tunable GAN, called α-GAN, parameterized by α∈
(0,∞], whi...
We consider three different variants of differential privacy (DP), namel...
We analyze the optimization landscape of a recently introduced tunable c...
We derive the optimal differential privacy (DP) parameters of a mechanis...
Privacy concerns have led to the development of privacy-preserving appro...
We present Generative Adversarial rePresentations (GAP) as a data-driven...
Recently, a parametrized class of loss functions called α-loss,
α∈ [1,∞]...
We present α-loss, α∈ [1,∞], a tunable loss function
for binary classifi...
Maximal α-leakage is a tunable measure of information leakage based on
t...
Consider a data publishing setting for a dataset composed of non-private...
In the first half of the paper, we introduce a tunable measure for
infor...
We present a data-driven framework called generative adversarial privacy...
A tunable measure for information leakage called maximal
α-leakage is in...
We study the problem of data disclosure with privacy guarantees, wherein...
We present a novel way to compare the statistical cost of privacy mechan...
Consider a data publishing setting for a data set with public and privat...
Preserving the utility of published datasets while simultaneously provid...