Data hiding in neural network prediction errors

Authors:
Guangjie Liu;Jinwei Wang;Shiguo Lian;Yuewei Dai;Zhiquan Wang
Affiliations:
Department of Automation, Nanjing University of Science & Technology, Nanjing, China;Department of Automation, Nanjing University of Science & Technology, Nanjing, China;Beijing R&D Center, France Telecom, Beijing, China;Department of Automation, Nanjing University of Science & Technology, Nanjing, China;Department of Automation, Nanjing University of Science & Technology, Nanjing, China
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
Year:
2006

Citing 3
Cited 0

Neural network design

Neural network design
A steganographic method for images by pixel-value differencing

Pattern Recognition Letters
Hiding secret data in images via predictive coding

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new and efficient image hiding scheme is proposed. Different from the existing methods, the secret data is embedded into the prediction errors produced by the neural network nonlinear predictor, and the non-uniform quantization method is used to embed secret data. The proposed method can achieve higher embedding payload while keeping smaller distortion, and experimental results are given to show the advantage of this scheme.