Deakin University
Browse

File(s) under permanent embargo

A multi-task learning CNN for image steganalysis

conference contribution
posted on 2018-01-01, 00:00 authored by X Yu, H Tan, H Liang, Chang-Tsun LiChang-Tsun Li, G Liao
Convolutional neural network (CNN) based image steganalysis are increasingly popular because of their superiority in accuracy. The most straightforward way to employ CNN for image steganalysis is to learn a CNN-based classifier to distinguish whether secret messages have been embedded into an image. However, it is difficult to learn such a classifier because of the weak stego signals and the limited useful information. To address this issue, in this paper, a multi-task learning CNN is proposed. In addition to the typical use of CNN, learning a CNN-based classifier for the whole image, our multi-task CNN is learned with an auxiliary task of the pixel binary classification, estimating whether each pixel in an image has been modified due to steganography. To the best of our knowledge, we are the first to employ CNN to perform the pixel-level classification of such type. Experimental results have justified the effectiveness and efficiency of the proposed multi-task learning CNN.

History

Event

IEEE Signal Processing Society. Conference (10th : 2018 : Hong Kong, China)

Series

IEEE Signal Processing Society Conference

Pagination

1 - 7

Publisher

Institute of Electrical and Electronics Engineers

Location

Hong Kong, China

Place of publication

Piscataway, N.J.

Start date

2018-12-11

End date

2018-12-13

ISBN-13

9781538665367

Language

eng

Publication classification

E1.1 Full written paper - refereed

Copyright notice

2018, IEEE

Editor/Contributor(s)

[Unknown]

Title of proceedings

WIFS 2018 Proceedings of the 10th IEEE International Workshop on Information Forensics and Security 2018

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC