Evaluation of deep learning and conventional approaches for image steganalysis

Tools

Xie, Guoliang and Zhao, Huimin and Zhao, Sophia and Marshall, Stephen; Ren, Jinchang and Ren, Jinchang and Hussain, Amir and Zhao, Huimin and Huang, Kaizhu and Zheng, Jiangbin and Cai, Jun and Chen, Rongjun and Xiao, Yinyin, eds. (2020) Evaluation of deep learning and conventional approaches for image steganalysis. In: Advances in Brain Inspired Cognitive Systems. Springer, Cham, Switzerland, pp. 342-352. ISBN 9783030394318 (https://doi.org/10.1007/978-3-030-39431-8_33)

[thumbnail of Xie-etal-BICS2019-Evaluation-of-deep-learning-and-conventional-approaches-for-image-steganalysis]
Preview
 Text. Filename: Xie_etal_BICS2019_Evaluation_of_deep_learning_and_conventional_approaches_for_image_steganalysis.pdf
Accepted Author Manuscript
Download (234kB)| Preview

Abstract

Steganography is the technique that's used to embed secret messages into digital media without changing their appearances. As a countermeasure to steganography, steganalysis detects the presence of hidden data in a digital content. For the last decade, the majority of image steganalysis approaches can be formed by two stages. The first stage is to extract effective features from the image content and the second is to train a classifier in machine learning by using the features from stage one. Ultimately the image steganalysis becomes a binary classification problem. Since Deep Learning related architecture unify these two stages and save researchers lots of time designing hand-crafted features, the design of a CNN-based steganalyzer has therefore received increasing attention over the past few years. In this paper, we will examine the development in image steganalysis, both in spatial domain and in JPEG domain, and discuss the future directions.

ORCID iDs

Xie, Guoliang, Zhao, Huimin, Zhao, Sophia and Marshall, Stephen ORCID logoORCID: https://orcid.org/0000-0001-7079-5628; Ren, Jinchang, Ren, Jinchang, Hussain, Amir, Zhao, Huimin, Huang, Kaizhu, Zheng, Jiangbin, Cai, Jun, Chen, Rongjun and Xiao, Yinyin
CORE (COnnecting REpositories)