Optimization method for steganalysis of convolutional neural network

Abstract

The invention discloses an optimization method for steganalysis of a convolutional neural network. The optimization method comprises the following steps that the intra-class aggregation degree of samples of the same class is visualized; and dimensionality reduction is carried out on a feature set corresponding to each sample point by adopting a nonlinear t-sne dimensionality reduction algorithm until the feature set is observed under a two-dimensional visual condition; steganography detection is performed on variable coefficients of the sample set; in order to eliminate the influence of the dimension and the measurement scale on the measurement of the aggregation degree of the samples, the variation coefficient is selected to measure the discrete degree of the samples so as to reflect the feature learning ability of the CNN steganalysis algorithm. The value of the variable coefficient is positively correlated with the discrete degree of the sample, and the larger the discrete degree of the sample is, the larger the variable coefficient is; the more the samples are gathered, the smaller the variable coefficient is; the feature set is adjusted based on the variation coefficient posteriori; a feature screening layer is added to manually filter the features obtained by the algorithm, some so-called'bad 'features unfavorable for later classification are removed, the accuracy of the algorithm can be improved to a certain extent, and the measurement effectiveness of the variable coefficient can be verified again.

Description

technical field [0001] The invention belongs to the field of image steganalysis, and in particular relates to space domain image information hiding and steganalysis. Background technique [0002] Information technology makes people's work and life more convenient, but also brings new threats and challenges to mankind. How to ensure information security is one of the typical problems. The most intuitive and basic method to ensure information security is to encrypt the information to be transmitted. Encryption methods can be divided into symmetric encryption and asymmetric encryption. AES and RSA are representatives of the corresponding fields. However, the ciphertext formed after information encryption is obviously unreadable and has obvious characteristics, so it is easy to be intercepted during the transmission process. In addition, before encryption, both parties need to go through a complicated key exchange process to ensure the security of the encryption key, and the c...

AI Technical Summary

Problems solved by technology

The core of the algorithm is the feature extraction module. The quality of the extracted steganographic features directly determines the quality of the algorithm. Therefore, in the traditional steganalysis algorithm, experts in the field will spend a lot of manpower and energy to mine prior knowledge. Fitting a steganographic feature set with a huge dimension is a huge workload, which increases the computational complexity of feature classification and with the innovation of steganography, the above workload, work complexity and work difficulty will be greatly increased

Images