grizzly/deneir
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

deblayage

Browse source
This commit is contained in:
Arthur Grisel-Davy 2023-07-05 15:04:20 -04:00
parent 60a01f8e46
commit c5befd3f7d
2 changed files with 18 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

32
DSD/qrs/main.tex
View file

@ -38,6 +38,7 @@
\normalsize *corresponding author \normalsize *corresponding author
} }
%+++++++++++++++++++++++++++++++++++++++++++ %+++++++++++++++++++++++++++++++++++++++++++
% use only for invited papers % use only for invited papers
@ -53,11 +54,11 @@ Enabling the definition and enforcement of high-level security policies requires
We present in this paper a novel time series, one-shot classifier called \gls{mad} specifically designed and evaluated for side-channel analysis. We present in this paper a novel time series, one-shot classifier called \gls{mad} specifically designed and evaluated for side-channel analysis.
\gls{mad} outperforms other traditional state detection solutions in terms of accuracy and, as importantly, Levenshtein distance of the state sequence. \gls{mad} outperforms other traditional state detection solutions in terms of accuracy and, as importantly, Levenshtein distance of the state sequence.
\end{abstract} \end{abstract}
\IEEEoverridecommandlockouts %\IEEEoverridecommandlockouts
\vspace{1.5ex} %\vspace{1.5ex}
\begin{keywords} %\begin{keywords}
\itshape component; formatting; style; styling; insert (key words) %\itshape component; formatting; style; styling; insert (key words)
\end{keywords} %\end{keywords}
% no keywords % no keywords
% For peer review papers, you can put extra information on the cover % For peer review papers, you can put extra information on the cover
@ -193,7 +194,6 @@ The pattern $\lambda$ is the \textit{unknown} pattern assigned to the samples in
\label{fig:overview} \label{fig:overview}
\end{figure} \end{figure}
\pagebreak
\section{Proposed Solution: MAD}\label{sec:solution} \section{Proposed Solution: MAD}\label{sec:solution}
\gls{mad}'s core idea separates it from other traditional sliding window algorithm. \gls{mad}'s core idea separates it from other traditional sliding window algorithm.
In \gls{mad}, the sample window around the sample to classify dynamically adapts for optimal context selection. In \gls{mad}, the sample window around the sample to classify dynamically adapts for optimal context selection.
@ -383,8 +383,18 @@ The lower the value of $\alpha$, the smaller the areas of attraction around each
Applying a coefficient to the thresholds produces a reduction of the radius of the area of attraction, not an homothety of the initial areas. Applying a coefficient to the thresholds produces a reduction of the radius of the area of attraction, not an homothety of the initial areas.
In other words, the shrink does not preserve the shape of the area. In other words, the shrink does not preserve the shape of the area.
For a value $\alpha < 0.5$, all areas become disks --- in the 2D representation --- and all shape information are lost. For a value $\alpha < 0.5$, all areas become disks --- in the 2D representation --- and all shape information are lost.
Figure~\ref{fig:areas} illustrate the areas of capture around the patterns for different values of $\alpha$.
The impact of the $\alpha$ coefficient on the classification is monotonic and predictable. \begin{figure}
\centering
\includegraphics[width=0.49\textwidth]{images/areas.pdf}
\caption{2D visualization of the areas of capture around each pattern as $\alpha$ changes. When $\alpha \ggg 2$, the areas of capture tends to equal these of a classic \gls{1nn}.}
\label{fig:areas}
\end{figure}
\agd{Increase font size}
The influence of the $\alpha$ coefficient on the classification is monotonic and predictable.
Because $\alpha$ influences the thresholds, changing $\alpha$ results in moving the transitions in the detected labels. Because $\alpha$ influences the thresholds, changing $\alpha$ results in moving the transitions in the detected labels.
In other words, a lower value of $\alpha$ expands the unknown segments while a higher value shrinks them until they disappear. In other words, a lower value of $\alpha$ expands the unknown segments while a higher value shrinks them until they disappear.
Figure~\ref{fig:alpha_impact} illustrates the impact $\alpha$ on the width of unknown segments. Figure~\ref{fig:alpha_impact} illustrates the impact $\alpha$ on the width of unknown segments.
@ -429,7 +439,6 @@ Figure~\ref{fig:alpha} presents the number of unknown samples in the classificat
\end{figure} \end{figure}
\pagebreak
\section{Case Study 1: Comparison with Other Methods} \section{Case Study 1: Comparison with Other Methods}
The first evaluation of \gls{mad} consists in the detection of the states for time series from various machines. The first evaluation of \gls{mad} consists in the detection of the states for time series from various machines.
We evaluate the performance of the proposed solution against other traditional methods to illustrate the capabilities and advantages of \gls{mad}. We evaluate the performance of the proposed solution against other traditional methods to illustrate the capabilities and advantages of \gls{mad}.
@ -566,14 +575,7 @@ With both performances metrics combined, \gls{mad} outperforms the other methods
\end{figure*} \end{figure*}
\begin{figure*}
\centering
\includegraphics[width=\textwidth]{images/areas.pdf}
\caption{2D visualization of the areas of capture around each pattern as $\alpha$ changes. When $\alpha \ggg 2$, the areas of capture tends to equal these of a classic \gls{1nn}.}
\label{fig:areas}
\end{figure*}
\pagebreak
\section{Case Study 2: Attack Scenarios} \section{Case Study 2: Attack Scenarios}
\section{Discussion}\label{sec:discussion} \section{Discussion}\label{sec:discussion}