2020
DOI: 10.1109/access.2020.3024193
|View full text |Cite
|
Sign up to set email alerts
|

High-Capacity Image Steganography Based on Improved FC-DenseNet

Abstract: Aiming at the problem that the traditional steganography based on carrier modification has the low steganographic capacity, a steganographic scheme based on Fully Convolutional Dense Connection Network (FC-DenseNet) is proposed. Since FC-DenseNet can effectively overcome the problems of gradient dissipation and gradient explosion, and a large number of features are multiplexed, the cascaded secret image and carrier image can reconstruct good image quality after entering the network. Effectively improve stegano… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
15
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 30 publications
(15 citation statements)
references
References 30 publications
0
15
0
Order By: Relevance
“…The proposed scheme replaces the extraction network with a structure similar to the hiding network, which improves the performance of the decryption network. Therefore, the proposed TRPSteg is also clearly different from the previous CNNbased image steganography schemes [15][16][17]. In addition, a novel strategy of recursive permutation is proposed to encrypt the secret image and further improve the security of the steganography model.…”
Section: Differences Between Trpsteg and Other Image Steganography Sc...mentioning
confidence: 90%
See 1 more Smart Citation
“…The proposed scheme replaces the extraction network with a structure similar to the hiding network, which improves the performance of the decryption network. Therefore, the proposed TRPSteg is also clearly different from the previous CNNbased image steganography schemes [15][16][17]. In addition, a novel strategy of recursive permutation is proposed to encrypt the secret image and further improve the security of the steganography model.…”
Section: Differences Between Trpsteg and Other Image Steganography Sc...mentioning
confidence: 90%
“…However, these works have one or more of the following shortcomings: (1) the colors of the generated steganographic images are distorted [18]; (2) the hiding capacity is limited in [15,[18][19][20][21]. (3) the model [15][16][17]22] does not fit the steganographic process well; and (4) the secret image is not encrypted and then steganographic in [16,21,23]; thus, it is not sufficiently secure.…”
Section: Introductionmentioning
confidence: 99%
“…One LSB is the most appropriate way of hiding information because of its reversibility, or you can say that robustness against different attacks [4]. This work mainly focuses on image steganography [5]. Therefore, the term cover object now becomes cover image.…”
Section: System Modelmentioning
confidence: 99%
“…Given the value of being able to hide the existence of data, researchers propose a range of stenographic techniques that work at various levels of the system stack. The most popular techniques work at the system level, hiding data in images [12,53], audio files [54], video files [40], and within file system metadata [5,30,35]. Another set of techniques hides data in the transmission of cover data across a network [55].…”
Section: Introductionmentioning
confidence: 99%