Reinforcement Learning Aided Network Architecture Generation for JPEG Image Steganalysis
Document Type
Conference Proceeding
Publication Date
6-22-2020
Abstract
The architectures of convolutional neural networks used in steganalysis have been designed heuristically. In this paper, an automatic Network Architecture Generation algorithm based on reinforcement learning for JPEG image Steganalysis (JS-NAG) has been proposed. Different from the automatic neural network generation methods in computer vision which are based on the strong content signals, steganalysis is based on the weak embedded signals, thus needs specific design. In the proposed method, the agent is trained to sequentially select some high-performing blocks using Q-learning to generate networks. An early stop strategy and a well-designed performance prediction function have been utilized to reduce the search time. To generate the optimal networks, hundreds of networks have been searched and trained on 3 GPUs for 15 days. To further improve the detection accuracy, we make an ensemble classifier out of the generated convolutional neural networks. The experimental results have shown that the proposed method significantly outperforms the current state-of-the-art CNN based methods.
Identifier
85087925629 (Scopus)
ISBN
[9781450370509]
Publication Title
Ih and Mmsec 2020 Proceedings of the 2020 ACM Workshop on Information Hiding and Multimedia Security
External Full Text Location
https://doi.org/10.1145/3369412.3395060
First Page
23
Last Page
32
Grant
61772571
Fund Ref
National Natural Science Foundation of China
Recommended Citation
Yang, Jianhua; Lu, Beiling; Xiao, Liang; Kang, Xiangui; and Shi, Yun Qing, "Reinforcement Learning Aided Network Architecture Generation for JPEG Image Steganalysis" (2020). Faculty Publications. 5209.
https://digitalcommons.njit.edu/fac_pubs/5209
