manos/the-last-thing
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Reviewed ou2018optimal

Browse Source
This commit is contained in:
Manos Katsomallos 2021-09-07 15:16:37 +03:00
parent d435ce1a0b
commit f19a16df5e
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
text/related/micro.tex
View File

@ -274,6 +274,22 @@ private and eligible for publishing.
The authors compare their design with that of~\cite{chen2012differentially} and~\cite{he2015dpt} by running several tests, and ascertain that it outperforms them in terms of data utility. The authors compare their design with that of~\cite{chen2012differentially} and~\cite{he2015dpt} by running several tests, and ascertain that it outperforms them in terms of data utility.
However, due to DP-Star's privacy budget distribution to its different phases, for small values of $\varepsilon$ the framework's privacy performance is inferior to that of its competitors. However, due to DP-Star's privacy budget distribution to its different phases, for small values of $\varepsilon$ the framework's privacy performance is inferior to that of its competitors.
% An Optimal Pufferfish Privacy Mechanism for Temporally Correlated Trajectories
% - microdata
% - finite (sequential)
% - batch
% - dependence (temporal)
% - local
% - event
% - differential privacy
% - perturbation (randomized response, Laplace)
\hypertarget{ou2018optimal}{Ou et al.}~\cite{ou2018optimal} designed \emph{FGS-Pufferfish} for publishing temporally correlated trajectory data while protecting temporal correlation.
FGS-Pufferfish transforms a user's daily trajectories into a set of sine and cosine waves of different frequencies along with the corresponding Fourier coefficients.
Then, it adds Laplace noise to the Fourier coefficients' geometric sum.
The authors obtain the optimal noisy Fourier coefficients by solving the constrained optimization problem via the Lagrange Multiplier method depending on the available privacy budget.
They evaluate both the location data utility and the temporal correlation utility.
The experimental evaluation shows that FGS-Pufferfish outperforms CTS-DP~\cite{wang2017cts} in terms of the trade-off between privacy and location utility.
\subsection{Infinite observation} \subsection{Infinite observation}
\label{subsec:micro-infinite} \label{subsec:micro-infinite}
@ -422,7 +438,7 @@ Last but not least, the technique requires the calculation of the temporal priva
% ON-OFF Privacy in the Presence of Correlation % ON-OFF Privacy in the Presence of Correlation
% ON-OFF Privacy Against Correlation Over Time % ON-OFF Privacy Against Correlation Over Time
% - microdata % - microdata
% - infinite % - infinite (sequential)
% - streaming % - streaming
% - dependence % - dependence
% - event % - event