Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning
In recent years, some research results have been achieved in the field of image steganalysis. However, there are still problems of difficulty in extracting steganographic features from images with low embedding rates and unsatisfactory detection performance of steganalysis. In this paper, we propose...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/4/969 |
_version_ | 1797621296146677760 |
---|---|
author | Shouyue Liu Chunying Zhang Liya Wang Pengchao Yang Shaona Hua Tong Zhang |
author_facet | Shouyue Liu Chunying Zhang Liya Wang Pengchao Yang Shaona Hua Tong Zhang |
author_sort | Shouyue Liu |
collection | DOAJ |
description | In recent years, some research results have been achieved in the field of image steganalysis. However, there are still problems of difficulty in extracting steganographic features from images with low embedding rates and unsatisfactory detection performance of steganalysis. In this paper, we propose an image steganalysis method based on the attention mechanism and transfer learning. The method constructs a network model based on a convolutional neural network, including a preprocessing layer, a transposed convolutional layer, an ordinary convolutional layer, and a fully connected layer. We introduce the efficient channel attention module after the ordinary convolutional layer to focus on the steganographic region of the image, capture the local cross-channel interaction information, realize the adaptive adjustment of feature weights, and enhance the ability to extract steganographic features. Meanwhile, we apply the transfer learning method to use the training model parameters of high embedding rate images as the initialization parameters of the training model of the low embedding rate to achieve feature migration and further improve the steganalysis performance of the low embedding rate. The experimental results show that compared to the typical Xu-Net and Yedroudj-Net models, the detection accuracy of the proposed method is improved by 16.36% to 30.66% and by 35.59 to 37.83% for the embedding rates of 0.05 bpp, 0.1 bpp, and 0.2 bpp, respectively. Compared to the state-of-the-art Shen-Net model with low embedding rates, the detection accuracy is improved by 3.43% to 6.41%. This demonstrates the higher detection performance of the proposed method for steganalysis of low embedding rate images. |
first_indexed | 2024-03-11T08:53:50Z |
format | Article |
id | doaj.art-60b992b0321146aebb1a950aebf6a3d6 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T08:53:50Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-60b992b0321146aebb1a950aebf6a3d62023-11-16T20:13:00ZengMDPI AGElectronics2079-92922023-02-0112496910.3390/electronics12040969Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer LearningShouyue Liu0Chunying Zhang1Liya Wang2Pengchao Yang3Shaona Hua4Tong Zhang5College of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaCollege of Science, North China University of Science and Technology, Tangshan 063210, ChinaIn recent years, some research results have been achieved in the field of image steganalysis. However, there are still problems of difficulty in extracting steganographic features from images with low embedding rates and unsatisfactory detection performance of steganalysis. In this paper, we propose an image steganalysis method based on the attention mechanism and transfer learning. The method constructs a network model based on a convolutional neural network, including a preprocessing layer, a transposed convolutional layer, an ordinary convolutional layer, and a fully connected layer. We introduce the efficient channel attention module after the ordinary convolutional layer to focus on the steganographic region of the image, capture the local cross-channel interaction information, realize the adaptive adjustment of feature weights, and enhance the ability to extract steganographic features. Meanwhile, we apply the transfer learning method to use the training model parameters of high embedding rate images as the initialization parameters of the training model of the low embedding rate to achieve feature migration and further improve the steganalysis performance of the low embedding rate. The experimental results show that compared to the typical Xu-Net and Yedroudj-Net models, the detection accuracy of the proposed method is improved by 16.36% to 30.66% and by 35.59 to 37.83% for the embedding rates of 0.05 bpp, 0.1 bpp, and 0.2 bpp, respectively. Compared to the state-of-the-art Shen-Net model with low embedding rates, the detection accuracy is improved by 3.43% to 6.41%. This demonstrates the higher detection performance of the proposed method for steganalysis of low embedding rate images.https://www.mdpi.com/2079-9292/12/4/969image steganalysislow embedding rateattention mechanismtransfer learningconvolutional neural network |
spellingShingle | Shouyue Liu Chunying Zhang Liya Wang Pengchao Yang Shaona Hua Tong Zhang Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning Electronics image steganalysis low embedding rate attention mechanism transfer learning convolutional neural network |
title | Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning |
title_full | Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning |
title_fullStr | Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning |
title_full_unstemmed | Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning |
title_short | Image Steganalysis of Low Embedding Rate Based on the Attention Mechanism and Transfer Learning |
title_sort | image steganalysis of low embedding rate based on the attention mechanism and transfer learning |
topic | image steganalysis low embedding rate attention mechanism transfer learning convolutional neural network |
url | https://www.mdpi.com/2079-9292/12/4/969 |
work_keys_str_mv | AT shouyueliu imagesteganalysisoflowembeddingratebasedontheattentionmechanismandtransferlearning AT chunyingzhang imagesteganalysisoflowembeddingratebasedontheattentionmechanismandtransferlearning AT liyawang imagesteganalysisoflowembeddingratebasedontheattentionmechanismandtransferlearning AT pengchaoyang imagesteganalysisoflowembeddingratebasedontheattentionmechanismandtransferlearning AT shaonahua imagesteganalysisoflowembeddingratebasedontheattentionmechanismandtransferlearning AT tongzhang imagesteganalysisoflowembeddingratebasedontheattentionmechanismandtransferlearning |