Steganographer identification of JPEG image based on feature selection and graph convolutional representation

Aiming at the problem that the feature dimension of JPEG image steganalysis is too high, which leads to the complexity of distance calculation between users and a decrease in the identification performance of the steganographer, a method for steganographer recognition based on feature selection and...

Full description

Saved in:
Bibliographic Details
Main Authors: Qianqian ZHANG, Yi ZHANG, Hao LI, Yuanyuan MA, Xiangyang LUO
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2023-07-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2023128
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850210629318606848
author Qianqian ZHANG
Yi ZHANG
Hao LI
Yuanyuan MA
Xiangyang LUO
author_facet Qianqian ZHANG
Yi ZHANG
Hao LI
Yuanyuan MA
Xiangyang LUO
author_sort Qianqian ZHANG
collection DOAJ
description Aiming at the problem that the feature dimension of JPEG image steganalysis is too high, which leads to the complexity of distance calculation between users and a decrease in the identification performance of the steganographer, a method for steganographer recognition based on feature selection and graph convolutional representation was proposed.Firstly, the steganalysis features of the user’s images were extracted, and the feature subset with highseparability was selected.Then, the users were represented as a graph, and the features of users were obtained by training the graph convolutional neural network.Finally, because inter-class separability and intra-class aggregation were considered, the features of users that could capture the differences between users were learned.For steganographers who use JPEG steganography, such as nsF5, UED, J-UNIWARD, and so on, to embed secret information in images, the proposed method can reduce the feature dimensions and computing.The identification accuracy of various payloads can reach more than 80.4%, and it has an obvious advantage at the low payload.
format Article
id doaj-art-67f5edb2a70c425095cb0781bb88d7d7
institution OA Journals
issn 1000-436X
language zho
publishDate 2023-07-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-67f5edb2a70c425095cb0781bb88d7d72025-08-20T02:09:44ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-07-014421822959384211Steganographer identification of JPEG image based on feature selection and graph convolutional representationQianqian ZHANGYi ZHANGHao LIYuanyuan MAXiangyang LUOAiming at the problem that the feature dimension of JPEG image steganalysis is too high, which leads to the complexity of distance calculation between users and a decrease in the identification performance of the steganographer, a method for steganographer recognition based on feature selection and graph convolutional representation was proposed.Firstly, the steganalysis features of the user’s images were extracted, and the feature subset with highseparability was selected.Then, the users were represented as a graph, and the features of users were obtained by training the graph convolutional neural network.Finally, because inter-class separability and intra-class aggregation were considered, the features of users that could capture the differences between users were learned.For steganographers who use JPEG steganography, such as nsF5, UED, J-UNIWARD, and so on, to embed secret information in images, the proposed method can reduce the feature dimensions and computing.The identification accuracy of various payloads can reach more than 80.4%, and it has an obvious advantage at the low payload.http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2023128steganalysis;steganographer identification;information hiding;JPEG image
spellingShingle Qianqian ZHANG
Yi ZHANG
Hao LI
Yuanyuan MA
Xiangyang LUO
Steganographer identification of JPEG image based on feature selection and graph convolutional representation
Tongxin xuebao
steganalysis;steganographer identification;information hiding;JPEG image
title Steganographer identification of JPEG image based on feature selection and graph convolutional representation
title_full Steganographer identification of JPEG image based on feature selection and graph convolutional representation
title_fullStr Steganographer identification of JPEG image based on feature selection and graph convolutional representation
title_full_unstemmed Steganographer identification of JPEG image based on feature selection and graph convolutional representation
title_short Steganographer identification of JPEG image based on feature selection and graph convolutional representation
title_sort steganographer identification of jpeg image based on feature selection and graph convolutional representation
topic steganalysis;steganographer identification;information hiding;JPEG image
url http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2023128
work_keys_str_mv AT qianqianzhang steganographeridentificationofjpegimagebasedonfeatureselectionandgraphconvolutionalrepresentation
AT yizhang steganographeridentificationofjpegimagebasedonfeatureselectionandgraphconvolutionalrepresentation
AT haoli steganographeridentificationofjpegimagebasedonfeatureselectionandgraphconvolutionalrepresentation
AT yuanyuanma steganographeridentificationofjpegimagebasedonfeatureselectionandgraphconvolutionalrepresentation
AT xiangyangluo steganographeridentificationofjpegimagebasedonfeatureselectionandgraphconvolutionalrepresentation