English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Image steganalysis is a special binary classification problem that aims toclassify natural cover images and suspected stego images which are the resultsof embedding very weak secret message signals into covers. How to effectivelysuppress cover image content and thus make the classification of cover imagesand stego images easier is the key of this task. Recent researches show thatConvolutional Neural Networks (CNN) are very effective to detect steganographyby learning discriminative features between cover images and their stegos.Several deep CNN models have been proposed via incorporating domain knowledgeof image steganography/steganalysis into the design of the network and achievestate of the art performance on standard database. Following such direction, wepropose a novel model called Cover Image Suppression Network (CIS-Net), whichimproves the performance of spatial image steganalysis by suppressing coverimage content as much as possible in model learning. Two novel layers, theSingle-value Truncation Layer (STL) and Sub-linear Pooling Layer (SPL), areproposed in this work. Specifically, STL truncates input values into a samethreshold when they are out of a predefined interval. Theoretically, we haveproved that STL can reduce the variance of input feature map withoutdeteriorating useful information. For SPL, it utilizes sub-linear powerfunction to suppress large valued elements introduced by cover image contentsand aggregates weak embedded signals via average pooling. Extensive experimentsdemonstrate the proposed network equipped with STL and SPL achieves betterperformance than rich model classifiers and existing CNN models on challengingsteganographic algorithms.

CIS-Net: A Novel CNN Model for Spatial Image Steganalysis via Cover Image Suppression