116 Hits in 3.5 sec

The secure steganography for hiding images via GAN

Zhangjie Fu, Fan Wang, Xu Cheng
2020 EURASIP Journal on Image and Video Processing  
In recent years, many scholars have applied various deep learning networks to the field of steganalysis to improve the accuracy of detection.  ...  Moreover, it utilizes the adversarial training between the encoder-decoder network and the steganalysis model to improve the ability to resist the detection of steganalysis models based on deep learning  ...  In 2017, Hayes and Danezis [23] constructed the encoderdecoder network called SteGAN to hide binary bitstream and extract it, and generated steganographic images via adversarial training. Tang et al  ... 
doi:10.1186/s13640-020-00534-2 fatcat:xshude3upzgojidnqjudspgyee

Weakening the Detecting Capability of CNN-based Steganalysis [article]

Sai Ma, Qingxiao Guan, Xianfeng Zhao, Yaqi Liu
2018 arXiv   pre-print
Most of the proposed steganalytic deep learning models are derived from neural networks applied in computer vision. These kinds of neural networks have distinguished performance.  ...  In this paper we propose a method to generate steganographic adversarial example in order to enhance the steganographic security of existing algorithms.  ...  steganographic adversarial example Inspired by [6] [7], we proposed a method to enhance the security of DM steganographic algorithms against deep learning based steganalysis.  ... 
arXiv:1803.10889v1 fatcat:vndpxapy7vcznh5efd5xolsfn4

A Novel Technique for Image Steganalysis Based on Separable Convolution and Adversarial Mechanism

Yuwei Ge, Tao Zhang, Haihua Liang, Qingfeng Jiang, Dan Wang
2021 Electronics  
In recent years, various deep steganalysis networks have been proposed in academia, and have achieved good detection performance.  ...  Compared with the traditional steganalysis methods based on deep learning, our method shows obvious improvements in both detection performance and training efficiency.  ...  Deep neural networks automatically obtain the feature representations for steganographic detection through sample training, avoiding the dependence on manually defined features.  ... 
doi:10.3390/electronics10222742 fatcat:o7exnpjzrbbozizqp7in2durtu

Learning Symmetric and Asymmetric Steganography via Adversarial Training [article]

Zheng Li, Ge Han, Yunqing Wei, Shanqing Guo
2019 arXiv   pre-print
than classic steganographic algorithms.  ...  Steganography refers to the art of concealing secret messages within multiple media carriers so that an eavesdropper is unable to detect the presence and content of the hidden messages.  ...  With the rise of deep learning in recent years, deep learning has been applied to steganography [6, 7] . The goal of Volkhonskiy et al.  ... 
arXiv:1903.05297v2 fatcat:st3fgj7avzgj3dxb3epsmrlo2e

CIS-Net: A Novel CNN Model for Spatial Image Steganalysis via Cover Image Suppression [article]

Songtao Wu, Sheng-hua Zhong, Yan Liu, Mengyuan Liu
2019 arXiv   pre-print
Several deep CNN models have been proposed via incorporating domain knowledge of image steganography/steganalysis into the design of the network and achieve state of the art performance on standard database  ...  Recent researches show that Convolutional Neural Networks (CNN) are very effective to detect steganography by learning discriminative features between cover images and their stegos.  ...  Fridrich, “Deep residual network [9] S. Lyu and H.  ... 
arXiv:1912.06540v1 fatcat:wiinc6uyo5hdldjicpmfwl6p6a

Steganalysis via a Convolutional Neural Network using Large Convolution Filters for Embedding Process with Same Stego Key [article]

Jean-François Couchot, Raphaël Couturier, Christophe Guyeux and Michel Salomon
2016 arXiv   pre-print
These kind of deep learning networks is so well-suited for classification tasks based on the detection of variations in 2D shapes that it is the state-of-the-art in many image recognition problems.  ...  A key knowledge of image steganalyzer, which combines relevant image features and innovative classification procedures, can be deduced by a deep learning approach called Convolutional Neural Networks (  ...  Some preliminary experiments made in the case of training-testing stego images mismatch show that some networks are able detect multiple steganographic algorithms.  ... 
arXiv:1605.07946v3 fatcat:xejdpmd34fdenpb3holcu4ximy

A Survey on Digital Image Steganography

Jiaxin Wang, Mengxin Cheng, Peng Wu, Beijing Chen
2019 Journal of Information Hiding and Privacy Protection  
Zheng, S.; Li, B. (2018): A novel image steganography method via deep convolutional generative adversarial networks. IEEE Access, vol. 6, pp. 38303-38314. Kekre, H. B.; Athawale, A. A.; Athawale, U.  ...  The existing steganography algorithms are classified into traditional algorithms and deep learning-based algorithms. Moreover, their advantages and weaknesses are pointed out.  ...  [Zhang, Dong and Liu (2018) ] proposed ISGAN (Invisible Steganography via Generative Adversarial Networks) by introducing the steganalysis network proposed by Xu et al.  ... 
doi:10.32604/jihpp.2019.07189 fatcat:6dnb6vpepjfhfkl45e46pkggha

Learning to Generate Steganographic Cover for Audio Steganography using GAN

Lang Chen, Rangding Wang, Diqun Yan, Jie Wang
2021 IEEE Access  
(a) (b) and (c) are the original waveform, the steganographic audio waveform and the residual waveform between (a) and (b), respectively.  ...  Similarly, (d) (e) and (f) are the original spectrogram, the steganographic audio spectrogram and the residual spectrogram between (d) and (e), respectively.  ... 
doi:10.1109/access.2021.3090445 fatcat:jahetjqwgjcapmz7qsqu3o2f3q

IAS-CNN: Image adaptive steganalysis via convolutional neural network combined with selection channel

Zhujun Jin, Yu Yang, Yuling Chen, Yuwei Chen
2020 International Journal of Distributed Sensor Networks  
To solve the limitation of manually designing residual extraction filters, we adopt the method of self-learning filter in the network.  ...  Nowadays, steganalysis based on deep learning generally has a large number of parameters, and its pertinence to adaptive steganography algorithms is weak.  ...  Thus, the dependencies can be used to detect the steganographic noise which can be applied to the steganalyzers.  ... 
doi:10.1177/1550147720911002 fatcat:cqpbw4h6fzdqteu7chlwgewhmm

Adaptive Spatial Steganography Based on Probability-Controlled Adversarial Examples [article]

Sai Ma and Qingxiao Guan and Xianfeng Zhao and Yaqi Liu
2019 arXiv   pre-print
With deep learning based steganalysis methods, we can enhance the security of existing steganographic methods via adversarial method.  ...  STEGANOGRAPHIC ADVERSARIAL ATTACK Since first proposal of deep learning based steganalysis, the combination of deep learning and steganalysis has been a mainstream of relevant research.  ... 
arXiv:1804.02691v3 fatcat:q4zfofimqfhp3mdkipoavl5k7q

Neural Reversible Steganography with Long Short-Term Memory

Ching-Chun Chang, Chi-Hua Chen
2021 Security and Communication Networks  
However, there is as yet no consensus on the use of deep neural networks in reversible steganography, a class of steganographic methods that permits the distortion caused by message embedding to be removed  ...  Rather than employing neural networks in the coding module of a reversible steganographic scheme, we instead apply them to an analytics module that exploits data redundancy to maximise steganographic capacity  ...  Shortcuts or skip connections are essential to deep neural networks.  ... 
doi:10.1155/2021/5580272 fatcat:g3teymmqmjb35c23muvtl3htfi

Search for Image Steganographic Policy with Adversary and Auxiliary Constrained Distance Measure

Lin Li, Mingyu Fan, Mingwei Tang
2022 IEEE Access  
Cover estimator, adversary, and steganographic policy are parameterized via neural networks.  ...  However, due to the difficulty of capturing the unknown distribution of the high-dimensional cover, it is challenging to design a steganographic scheme from the view of traditional and deep learning-based  ...  Cover estimator, adversary, and steganographic policy are parameterized via neural networks.  ... 
doi:10.1109/access.2022.3164666 fatcat:rtvlge6ivnbfphn5leush535d4

Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels [article]

Wei Wang, Jing Dong, Yinlong Qian, Tieniu Tan
2018 arXiv   pre-print
However, the proposed deep models have been often learned from pre-calculated noise residuals with fixed high-pass filters rather than from raw images.  ...  Besides class labels, we make use of additional pixel level supervision of cover-stego image pair to jointly and iteratively train the proposed network which consists of a residual calculation network  ...  Deep learning for steganalysis via convolutional neural networks.  ... 
arXiv:1806.10443v1 fatcat:x3e5a22tcbe5vd7sa26kzgveq4

Deep Learning for Predictive Analytics in Reversible Steganography [article]

Ching-Chun Chang, Xu Wang, Sisheng Chen, Isao Echizen, Victor Sanchez, Chang-Tsun Li
2022 arXiv   pre-print
Deep learning is regarded as a promising solution for reversible steganography.  ...  Experimental results show that state-of-the-art steganographic performance can be achieved with advanced neural network models.  ...  The foundations of deep learning are neural networks, or connectionist systems, which are capable of discovering intricate structures in high-dimensional data via multiple layers of artificial neurons.  ... 
arXiv:2106.06924v2 fatcat:frp7oyqhinajlflhtsvvudxss4

CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images [article]

Shunquan Tan, Weilong Wu, Zilong Shao, Qiushi Li, Bin Li, Jiwu Huang
2020 arXiv   pre-print
In this paper we propose CALPA-NET, a ChAnneL-Pruning-Assisted deep residual network architecture search approach to shrink the network structure of existing vast, over-parameterized deep-learning based  ...  Over the past few years, detection performance improvements of deep-learning based steganalyzers have been usually achieved through structure expansion.  ...  In this paper, we propose CALPA-NET, a channel-pruningassisted deep residual network architecture search approach to shrink the network structure of existing vast, overparameterized deep-learning based  ... 
arXiv:1911.04657v2 fatcat:fvj2tygabrgxnoqljv7ti2ucbi
« Previous Showing results 1 — 15 out of 116 results