The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
다양한 스테가노그래피 방법으로 인해 발생하는 이미지 변형은 일반적으로 매우 작고 매우 유사하므로 감지 및 식별이 어려운 작업입니다. 최근 딥러닝을 활용한 스테가노그래피 기법은 높은 정확도를 달성했지만, 특정 스테가노그래피 기법이 적용된 스테고 영상을 검출하도록 만들어졌다. 이 편지에서는 계층적 잔류 신경망(ResNet)을 사용하여 네 가지 공간 스테가노그래피 방법(예: LSB, PVD, WOW 및 S-UNIWARD)을 감지(예: 스테고와 표지 이미지 간의 분류)하고 식별할 수 있는 스테가나리틱 방법을 제안합니다. 실험 결과에 따르면 계층적 ResNet을 사용하면 79.71진 분류에서 23%의 분류율을 달성하며 이는 일반 CNN(일반 CNN)을 사용하는 경우에 비해 약 XNUMX% 더 높습니다.
Sanghoon KANG
Pukyong National University
Hanhoon PARK
Pukyong National University
Jong-Il PARK
Hanyang University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Sanghoon KANG, Hanhoon PARK, Jong-Il PARK, "Identification of Multiple Image Steganographic Methods Using Hierarchical ResNets" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 2, pp. 350-353, February 2021, doi: 10.1587/transinf.2020EDL8116.
Abstract: Image deformations caused by different steganographic methods are typically extremely small and highly similar, which makes their detection and identification to be a difficult task. Although recent steganalytic methods using deep learning have achieved high accuracy, they have been made to detect stego images to which specific steganographic methods have been applied. In this letter, a staganalytic method is proposed that uses hierarchical residual neural networks (ResNet), allowing detection (i.e. classification between stego and cover images) and identification of four spatial steganographic methods (i.e. LSB, PVD, WOW and S-UNIWARD). Experimental results show that using hierarchical ResNets achieves a classification rate of 79.71% in quinary classification, which is approximately 23% higher compared to using a plain convolutional neural network (CNN).
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8116/_p
부
@ARTICLE{e104-d_2_350,
author={Sanghoon KANG, Hanhoon PARK, Jong-Il PARK, },
journal={IEICE TRANSACTIONS on Information},
title={Identification of Multiple Image Steganographic Methods Using Hierarchical ResNets},
year={2021},
volume={E104-D},
number={2},
pages={350-353},
abstract={Image deformations caused by different steganographic methods are typically extremely small and highly similar, which makes their detection and identification to be a difficult task. Although recent steganalytic methods using deep learning have achieved high accuracy, they have been made to detect stego images to which specific steganographic methods have been applied. In this letter, a staganalytic method is proposed that uses hierarchical residual neural networks (ResNet), allowing detection (i.e. classification between stego and cover images) and identification of four spatial steganographic methods (i.e. LSB, PVD, WOW and S-UNIWARD). Experimental results show that using hierarchical ResNets achieves a classification rate of 79.71% in quinary classification, which is approximately 23% higher compared to using a plain convolutional neural network (CNN).},
keywords={},
doi={10.1587/transinf.2020EDL8116},
ISSN={1745-1361},
month={February},}
부
TY - JOUR
TI - Identification of Multiple Image Steganographic Methods Using Hierarchical ResNets
T2 - IEICE TRANSACTIONS on Information
SP - 350
EP - 353
AU - Sanghoon KANG
AU - Hanhoon PARK
AU - Jong-Il PARK
PY - 2021
DO - 10.1587/transinf.2020EDL8116
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2021
AB - Image deformations caused by different steganographic methods are typically extremely small and highly similar, which makes their detection and identification to be a difficult task. Although recent steganalytic methods using deep learning have achieved high accuracy, they have been made to detect stego images to which specific steganographic methods have been applied. In this letter, a staganalytic method is proposed that uses hierarchical residual neural networks (ResNet), allowing detection (i.e. classification between stego and cover images) and identification of four spatial steganographic methods (i.e. LSB, PVD, WOW and S-UNIWARD). Experimental results show that using hierarchical ResNets achieves a classification rate of 79.71% in quinary classification, which is approximately 23% higher compared to using a plain convolutional neural network (CNN).
ER -