Classification of Multiple Steganographic Algorithms Using Hierarchical CNNs and ResNets

Sanghoon Kang, Hanhoon Park, Jong Il Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In general, image deformations caused by different steganographic algorithms are extremely small and of high similarity. Therefore, detecting and identifying multiple steganographic algorithms are not easy. Although recent steganalytic methods using deep learning showed highly improved detection accuracy, they were dedicated to binary classification, i.e., classifying between cover images and their stego images generated by a specific steganographic algorithm. In this paper, we aim at achieving quinary classification, i.e., detecting (=classifying between stego and cover images) and identifying four spatial steganographic algorithms (LSB, PVD, WOW, and S-UNIWARD), and propose to use a hierarchical structure of convolutional neural networks (CNN) and residual neural networks (ResNet). Experimental results show that the proposed method can improve the classification accuracy by 17.71% compared to the method that uses a single CNN.

Original languageEnglish
Title of host publicationProceedings of International Conference on Smart Computing and Cyber Security - Strategic Foresight, Security Challenges and Innovation SMARTCYBER 2020
EditorsPrasant Kumar Pattnaik, Mangal Sain, Ahmed A. Al-Absi, Pardeep Kumar
PublisherSpringer Science and Business Media Deutschland GmbH
Pages365-373
Number of pages9
ISBN (Print)9789811579899
DOIs
StatePublished - 2021
EventInternational Conference on Smart Computing and Cyber Security: Strategic Foresight, Security Challenges and Innovation, SMARTCYBER 2020 - Goseong, Korea, Republic of
Duration: 2020 Apr 232020 Apr 24

Publication series

NameLecture Notes in Networks and Systems
Volume149
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Conference on Smart Computing and Cyber Security: Strategic Foresight, Security Challenges and Innovation, SMARTCYBER 2020
Country/TerritoryKorea, Republic of
CityGoseong
Period20/04/2320/04/24

Keywords

  • Convolutional neural network
  • Hierarchical structure
  • Image steganography
  • Quinary classification
  • Residual neural network
  • Steganalysis

Fingerprint

Dive into the research topics of 'Classification of Multiple Steganographic Algorithms Using Hierarchical CNNs and ResNets'. Together they form a unique fingerprint.

Cite this