Title
A novel natural language steganographic framework based on image description neural network
Abstract
•A carrier-less text steganography based on CNN-LSTM network is proposed.•SSH scheme based on beam search can be applied in model sharing situation.•HH scheme for model-free extraction with hash function is proposed.•The tradeoff between text quality and embedded capacity can be balanced.•The proposed schemes achieve high text quality, invisibility, and security.
Year
DOI
Venue
2019
10.1016/j.jvcir.2019.03.016
Journal of Visual Communication and Image Representation
Keywords
Field
DocType
Natural language steganography,Image description,Neural network,Embedding capacity,BLEU,Perplexity
Data mining,Steganography,Embedding,Pattern recognition,Convolutional neural network,Natural language,Artificial intelligence,Data extraction,Hash function,Artificial neural network,Sentence,Mathematics
Journal
Volume
ISSN
Citations 
61
1047-3203
1
PageRank 
References 
Authors
0.35
0
5
Name
Order
Citations
PageRank
Juan Wen1113.17
Xuejing Zhou240.73
Mengdi Li331.05
Ping Zhong4103.16
Yiming Xue5176.28