JPEG-Phase-Aware Convolutional Neural Network for Steganalysis of JPEG Images

被引：121

作者：

Chen, Mo ^{[1
]}

Sedighi, Vahid ^{[1
]}

Boroumand, Mehdi ^{[1
]}

Fridrich, Jessica ^{[1
]}

机构：

[1] SUNY Binghamton, Dept ECE, Binghamton, NY 13902 USA

来源：

IH&MMSEC'17: PROCEEDINGS OF THE 2017 ACM WORKSHOP ON INFORMATION HIDING AND MULTIMEDIA SECURITY | 2017年

关键词：

Steganography; steganalysis; convolutional neural network; JPEG; phase aware; catalyst kernel; MODEL;

D O I：

10.1145/3082031.3083248

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

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.

引用

页码：75 / 84

页数：10