Recent Advances of Image Steganography With Generative Adversarial Networks

Liu, Jia; Yan, K.; Zhang, Zhuo; Yu, Lei; Li, Jun; Zhang, Minqing; Yang, Xiaoyuan

doi:10.1109/access.2020.2983175

Cited by 68 publications

(20 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has revolutionised both academia and industry [23]. e phenomenal advances in deep learning have also introduced a paradigm shift in digital steganography [24][25][26][27][28][29]. However, research on reversible steganography with deep neural networks remains largely undeveloped.…”

Section: Introductionmentioning

confidence: 99%

Neural Reversible Steganography with Long Short-Term Memory

Chang

2021

Security and Communication Networks

View full text Add to dashboard Cite

Deep learning has brought about a phenomenal paradigm shift in digital steganography. 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. The underdevelopment of the field of reversible steganography with deep learning can be attributed to the perception that perfect reversal of steganographic distortion seems scarcely achievable, due to the lack of transparency and interpretability of neural networks. 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. State-of-the-art reversible steganographic schemes for digital images are based primarily on a histogram-shifting method in which the analytics module is often modelled as a pixel intensity predictor. In this paper, we propose to refine the prior estimation from a conventional linear predictor through a neural network model. The refinement can be to some extent viewed as a low-level vision task (e.g., noise reduction and super-resolution imaging). In this way, we explore a leading-edge neuroscience-inspired low-level vision model based on long short-term memory with a brief discussion of its biological plausibility. Experimental results demonstrated a significant boost contributed by the neural network model in terms of prediction accuracy and steganographic rate-distortion performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural Reversible Steganography with Long Short-Term Memory

Chang

2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…It is designed for both steganographic applications and for digital watermarks embedding. The paper [46] provides an overview of various strategies for digital image data hiding using the generative adversarial network: cover modification, cover selection, and cover synthesis.…”

Section: B Frequency Data Hidingmentioning

confidence: 99%

Digital Steganography and Watermarking for Digital Images: A Review of Current Research Directions

2020

View full text Add to dashboard Cite

The development of information technology has led to a significant increase in the share of multimedia traffic in data networks. This has necessitated to solve the following information security tasks in relation to multimedia data: protection against leakage of confidential information, as well as identifying the source of the leak; ensuring the impossibility of unauthorized changes; copyright protection for digital objects. To solve such kind of problems, methods of steganography and watermarking are designed that implement embedding in digital objects hidden information sequences for various purposes. In this paper, an overview of promising research in the specified area is provided. First of all, we provide basic information about this field of research and consider the main applications of its methods. Next, we review works demonstrating current trends in the development of methods and algorithms for data hiding in digital images. This review is not exhaustive; it focuses on contemporary works illustrating current research directions in the field of information embedding in digital images. This is the main feature of review, which distinguishes it from previously published reviews. The paper concludes with an analysis of identified problems in the field of digital steganography and digital watermarking.

show abstract

“…The messages are even adapted to the content of the files to become more imperceptible. The modification of images (i.e., the most common type of digital media) is used in several applications; for example, to transmit legal and secure information [1], for criminal or terrorist purposes [2], or attacks on social media such as Instagram [3]. With this in mind, legal entities require detecting when image files have been modified to send confidential information.…”

Section: Introductionmentioning

confidence: 99%

GBRAS-Net: A Convolutional Neural Network Architecture for Spatial Image Steganalysis

et al. 2021

View full text Add to dashboard Cite

Advances in Deep Learning (DL) have provided alternative approaches to various complex problems, including the domain of spatial image steganalysis using Convolutional Neural Networks (CNN). Several CNN architectures have been developed in recent years, which have improved the detection accuracy of steganographic images. This work presents a novel CNN architecture which involves a preprocessing stage using filter banks to enhance steganographic noise, a feature extraction stage using depthwise and separable convolutional layers, and skip connections. Performance was evaluated using the BOSSbase 1.01 and BOWS 2 datasets with different experimental setups, including adaptive steganographic algorithms, namely WOW, S-UNIWARD, MiPOD, HILL and HUGO. Our results outperformed works published in the last few years in every experimental setting. This work improves classification accuracies on all algorithms and bits per pixel (bpp), reaching 80.3% on WOW with 0.2 bpp and 89.8% on WOW with 0.4 bpp, 73.6% and 87.1% on S-UNIWARD (0.2 and 0.4 bpp respectively), 68.3% and 81.4% on MiPOD (0.2 and 0.4 bpp), 68.5% and 81.9% on HILL (0.2 and 0.4 bpp), 74.6% and 84.5% on HUGO (0.2 and 0.4 bpp), using BOSSbase 1.01 test data.

show abstract

Recent Advances of Image Steganography With Generative Adversarial Networks

Cited by 68 publications

References 85 publications

Neural Reversible Steganography with Long Short-Term Memory

Neural Reversible Steganography with Long Short-Term Memory

Digital Steganography and Watermarking for Digital Images: A Review of Current Research Directions

GBRAS-Net: A Convolutional Neural Network Architecture for Spatial Image Steganalysis

Contact Info

Product

Resources

About