1 \subsection{Steganalysis}
5 The quality of our approach has been evaluated through the two
6 AUMP~\cite{Fillatre:2012:ASL:2333143.2333587}
7 and Ensemble Classifier~\cite{DBLP:journals/tifs/KodovskyFH12} based steganalysers.
8 Both aims at detecting hidden bits in grayscale natural images and are
9 considered as the state of the art of steganalysers in spatial domain~\cite{FK12}.
10 The former approach is based on a simplified parametric model of natural images.
11 Parameters are firstly estimated and a adaptive Asymptotically Uniformly Most Powerful
12 (AUMP) test is designed (theoretically and practically) to check whether
13 a natural image has stego content or not.
14 In the latter, the authors show that the
15 machine learning step, (which is often
16 implemented as support vector machine)
17 can be a favourably executed thanks to an Ensemble Classifiers.
