TY - GEN
T1 - TCNN
T2 - 16th International Conference on Security and Privacy in Communication Networks, SecureComm 2020
AU - Chen, Zhili
AU - Yang, Baohua
AU - Wu, Fuhu
AU - Ren, Shuai
AU - Zhong, Hong
N1 - Publisher Copyright:
© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.
PY - 2020
Y1 - 2020
N2 - Recently, convolutional neural network (CNN) based methods have achieved significantly better performance compared to conventional methods based on hand-crafted features for image steganalysis. However, as far as we know, existing CNN based methods extract features either with constrained (even fixed), or random (i.e., randomly initialized) convolutional kernels, and this leads to limitations as follows. First, it is unlikely to obtain optimal results for exclusive use of constrained kernels due to the constraints. Second, it becomes difficult to get optimal when using merely random kernels because of the large parameter space to learn. In this paper, to overcome these limitations, we propose a two-way convolutional neural network (TCNN) for image steganalysis, by combining both constrained and random convolutional kernels, and designing respective sub-networks. Intuitively, by complementing one another, the combination of these two kinds of kernels can enrich features extracted, ease network convergence, and thus provide better results. Experimental results show that the proposed TCNN steganalyzer is superior to the state-of-the-art CNN-based and hand-crafted features-based methods, at different payloads.
AB - Recently, convolutional neural network (CNN) based methods have achieved significantly better performance compared to conventional methods based on hand-crafted features for image steganalysis. However, as far as we know, existing CNN based methods extract features either with constrained (even fixed), or random (i.e., randomly initialized) convolutional kernels, and this leads to limitations as follows. First, it is unlikely to obtain optimal results for exclusive use of constrained kernels due to the constraints. Second, it becomes difficult to get optimal when using merely random kernels because of the large parameter space to learn. In this paper, to overcome these limitations, we propose a two-way convolutional neural network (TCNN) for image steganalysis, by combining both constrained and random convolutional kernels, and designing respective sub-networks. Intuitively, by complementing one another, the combination of these two kinds of kernels can enrich features extracted, ease network convergence, and thus provide better results. Experimental results show that the proposed TCNN steganalyzer is superior to the state-of-the-art CNN-based and hand-crafted features-based methods, at different payloads.
KW - Convolutional neural network
KW - Steganalysis
KW - Two-way
UR - https://www.scopus.com/pages/publications/85098256984
U2 - 10.1007/978-3-030-63086-7_29
DO - 10.1007/978-3-030-63086-7_29
M3 - 会议稿件
AN - SCOPUS:85098256984
SN - 9783030630850
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
SP - 509
EP - 514
BT - Security and Privacy in Communication Networks - 16th EAI International Conference, SecureComm 2020, Proceedings
A2 - Park, Noseong
A2 - Sun, Kun
A2 - Foresti, Sara
A2 - Butler, Kevin
A2 - Saxena, Nitesh
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 21 October 2020 through 23 October 2020
ER -