Anti-steganalysis for image on convolutional neural networks

被引：0
作者：
Shiyu Li
Dengpan Ye
Shunzhi Jiang
Changrui Liu
Xiaoguang Niu
Xiangyang Luo
机构：
[1] Wuhan University,School of Cyber Science and Engineering
[2] Wuhan University,School of Computer Science
[3] State Key Laboratory of Mathematical Engineering and Advanced Computing,undefined
来源：
Multimedia Tools and Applications | 2020年 / 79卷
关键词：
Anti-steganalysis; CNN; Adversarial example;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Nowadays, convolutional neural network (CNN) based steganalysis methods achieved great performance. While those methods are also facing security problems. In this paper, we proposed an attack scheme aiming at CNN based steganalyzer including two different attack methods 1) the LSB-Jstego Gradient Based Attack; 2) LSB-Jstego Evolutionary Algorithms Based Attack. The experiment results show that the attack strategies could achieve 96.02% and 90.25% success ratio separately on the target CNN. The proposed attack scheme is an effective way to fool the CNN based steganalyzer and in addition demonstrates the vulnerability of the neural networks in steganalysis.
引用
收藏
页码：4315 / 4331
页数：16
相关论文
共 35 条
[1]  
Das S(2011)Differential evolution: a survey of the state-of-the-art IEEE Trans Evol Comput 15 4-31
[2]  
Suganthan PN(2012)Rich models for steganalysis of digital images IEEE Trans Inf Forensics Secur 7 868-882
[3]  
Fridrich J(2016)Steganalysis of hugo steganography based on parameter recognition of syndrome-trellis-codes Multimed Tools Appl 75 13557-13583
[4]  
Kodovsky J(2016)Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch Electron Imaging 2016 1-11
[5]  
Luo X(1997)Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces J Glob Optim 11 341-359
[6]  
Song X(2017)Forensics feature analysis in quaternion wavelet domain for distinguishing photographic images and computer graphics Multimed Tools Appl 76 23721-23737
[7]  
Li X(2008)The evolution of video quality measurement: from psnr to hybrid metrics IEEE Trans Broadcast 54 660-668
[8]  
Zhang W(2016)Structural design of convolutional neural networks for steganalysis IEEE Signal Process Lett 23 708-712
[9]  
Lu J(2017)Deep learning hierarchical representations for image steganalysis IEEE Trans Inf Forensics Secur 12 2545-2557
[10]  
Yang C(2018)On the fault-tolerant performance for a class of robust image steganography Signal Process 146 99-111
1234