Steganalysis hybrid integration method based on deep learning

Abstract

The invention relates to a steganalysis hybrid integration method based on deep learning. The method comprises the following specific operation steps: dividing a data set, obtaining a residual image through a high-pass filter, constructing a convolutional neural network, training a network model, storing a plurality of optimal models, respectively loading the models, and storing the output of a pooling layer as a feature; Changing a high-pass filter, generating different residual images to obtain difference features, and performing feature fusion to obtain high-dimensional features; Inputtingthe high-dimensional features into the PCA for dimension reduction; Inputting the features subjected to dimension reduction into an xgboost classifier, an SVM classifier and a KNN classifier for classification; And carrying out integrated learning on the obtained classification result, and carrying out weighted voting to obtain a final classification result. According to the invention, the classification accuracy of the classifier can be effectively improved.

Description

technical field [0001] The invention relates to a steganalysis hybrid integration method based on deep learning. Background technique [0002] Steganography technology is an important branch of information hiding technology. Steganography uses digital media such as images and texts as carriers to embed secret information to be sent into the carrier signal and pass through public channels in a way that does not attract the attention of third parties. Steganalysis technology mainly reveals the existence of secret information in digital media. [0003] Image steganalysis is to judge whether an image contains secret information. In steganalysis technology, the extraction of image features is very important. With the continuous improvement of steganography technology, the design of features is becoming more and more complex. Convolutional neural network has attracted much attention because it can automatically extract features. Convolutional neural network is an effective deep ...

AI Technical Summary

Problems solved by technology

Among the existing classification methods, the convolutional neural network has achieved good results, but because the structure of the Sigmoid classifier matched by the convolutional neural network is simple, the classification effect is not as good as the traditional machine learning classifier.

Images