Steganalysis Based on Awareness of Selection-Channel and Deep Learning

Yang, Jianhua; Li, Kai; Kang, Xiangui; Wong, Edward K.; Shi, Yun-Qing

doi:10.1007/978-3-319-64185-0_20

Cited by 33 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aiming at the problem of the severe fluctuation of the loss during training, Songtao et al studied the setting of the BN parameters [24]. Yang et al proposed a CNN combined with a channel selection mechanism [25]. Sedighi et al designed a CNN with a Gaussian activation function to implement histogram features [26].…”

Section: Introductionmentioning

confidence: 99%

A New Convolutional Neural Network-Based Steganalysis Method for Content-Adaptive Image Steganography in the Spatial Domain

et al. 2020

View full text Add to dashboard Cite

Convolutional neural network-based methods are attracting increasing attention in steganalysis. However, steganalysis for content-adaptive image steganography in the spatial domain is still a difficult problem. In this paper, a new convolutional neural network-based steganalysis approach was proposed with two contributions. 1) By adding more convolutional layers in the lower part of the model, we proposed a new arrangement of convolutional layers and pooling layers, which can process the local information better than the existing CNN models in steganalysis. 2) By adding the global average pooling layer before the softmax layer instead of using global average pooling before the fully connected layer, the global average pooling was placed in a better position for steganalysis. Two state-of-the-art steganographic algorithms in the spatial domain, namely, WOW and S-UNIWARD, were used to evaluate the effectiveness of our model. The experimental results on BOSSbase showed that the proposed CNN could obtain better steganalysis performance than YeNet across all tested algorithms when the payloads were 0.2, 0.3, and 0.4 bpp.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Convolutional Neural Network-Based Steganalysis Method for Content-Adaptive Image Steganography in the Spatial Domain

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Steganalysis & steganography play hide and seek game [4]. Because of the advancement in deep learning steganalytic algorithms [5], [6], [7], [8], [29], [30] the task of designing more reliable & robust steganographic framework becoming more and more imperative. Image steganography and steganalysis received a lot of attention from law enforcement agencies and social media due to easy of multimedia communication through the internet.…”

Section: Introductionmentioning

confidence: 99%

“…Selection-channel-aware based steganalysis approaches effectively detecting content-adaptive steganography schemes. Yang et al [30] and Ye et al [28] proposed methods to integrate the selection channel information in their networks. But designed this kind of features take a lot of time and efforts.…”

Section: Introductionmentioning

confidence: 99%

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

2020

KSII TIIS

View full text Add to dashboard Cite

Steganalysis & steganography have witnessed immense progress over the past few years by the advancement of deep convolutional neural networks (DCNN). In this paper, we analyzed current research states from the latest image steganography and steganalysis frameworks based on deep learning. Our objective is to provide for future researchers the work being done on deep learning-based image steganography & steganalysis and highlights the strengths and weakness of existing up-to-date techniques. The result of this study opens new approaches for upcoming research and may serve as source of hypothesis for further significant research on deep learning-based image steganography and steganalysis. Finally, technical challenges of current methods and several promising directions on deep learning steganography and steganalysis are suggested to illustrate how these challenges can be transferred into prolific future research avenues.

show abstract

“…The process of features optimization used swarm-based optimization algorithms [9,10,21]. The swarm-based algorithms are multi-objective and multi constraint-based fitness function and generate a better optimal solution instead of unguided algorithms for the optimization of features used particle swarm optimization and ant colony optimization [13][14][15][16][17][18]. The particle and ant colony optimization both are used features optimization for better selection and generation of patterns.…”

Section: Introductionmentioning

confidence: 99%

Optimized Features of SIFT Transform Function for Digital Image Watermarking using Hybrid Swarm Intelligence and Neural Network

Kumar¹,

Sharma²

2019

IJRTE

View full text Add to dashboard Cite

Authentication of digital multi-media is a challenging task in the current scenario of internet technology for the authentication of digital multi-media data used digital watermarking techniques. The feature-based watermarking techniques provide the robustness of digital watermarking methods. In this paper proposed optimized features based digital watermarking techniques using a neural network. For the process of features, optimization used hybrid swarm intelligence algorithms. The hybrid algorithms are a combination of PSO and ACO. The PSO used as feature optimizer and ACO used for the selection of features point for the processing of neural network models. Two neural networks models used BP and RBF. The property of both models is different for the processing of data and desired output for the enhancement of the proposed model used cascaded neural network models using BP and RBF. The cascaded models generate dynamic patterns for the embedding of a digital watermark. The dynamic patterns provide the randomness of the pixel value and decrease the value of attack predication. The proposed algorithms have been tested on an extensive database of 300 images. The analysis of the proposed algorithm is satisfactory against different types of attacks and enhance the strength of robustness.

show abstract

Steganalysis Based on Awareness of Selection-Channel and Deep Learning

Cited by 33 publications

References 25 publications

A New Convolutional Neural Network-Based Steganalysis Method for Content-Adaptive Image Steganography in the Spatial Domain

A New Convolutional Neural Network-Based Steganalysis Method for Content-Adaptive Image Steganography in the Spatial Domain

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

Optimized Features of SIFT Transform Function for Digital Image Watermarking using Hybrid Swarm Intelligence and Neural Network

Contact Info

Product

Resources

About