Skip to main navigation Skip to search Skip to main content

JPEG-phase-aware convolutional neural network for steganalysis of JPEG images

  • State University of New York Binghamton University

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

185 Scopus citations

Abstract

Detection of modern JPEG steganographic algorithms has traditionally relied on features aware of the JPEG phase. In this paper, we port JPEG-phase awareness into the architecture of a convolutional neural network to boost the detection accuracy of such detectors. Another innovative concept introduced into the detector is the "catalyst kernel" that, together with traditional high-pass filters used to pre-process images allows the network to learn kernels more relevant for detection of stego signal introduced by JPEG steganography. Experiments with J-UNIWARD and UED-JC embedding algorithms are used to demonstrate the merit of the proposed design.

Original languageEnglish
Title of host publicationIH and MMSec 2017 - Proceedings of the 2017 ACM Workshop on Information Hiding and Multimedia Security
PublisherAssociation for Computing Machinery, Inc
Pages75-84
Number of pages10
ISBN (Electronic)9781450350617
DOIs
StatePublished - Jun 20 2017
Event5th ACM Workshop on Information Hiding and Multimedia Security Workshop, IH and MMSec 2017 - Philadelphia, United States
Duration: Jun 20 2017Jun 22 2017

Publication series

NameIH and MMSec 2017 - Proceedings of the 2017 ACM Workshop on Information Hiding and Multimedia Security

Conference

Conference5th ACM Workshop on Information Hiding and Multimedia Security Workshop, IH and MMSec 2017
Country/TerritoryUnited States
CityPhiladelphia
Period06/20/1706/22/17

Keywords

  • Catalyst kernel
  • Convolutional neural network
  • JPEG
  • Phase aware
  • Steganalysis
  • Steganography

Fingerprint

Dive into the research topics of 'JPEG-phase-aware convolutional neural network for steganalysis of JPEG images'. Together they form a unique fingerprint.

Cite this