A Survey of Image Information Hiding Algorithms Based on Deep Learning
29 Dec 2018-Cmes-computer Modeling in Engineering & Sciences (Computers, Materials and Continua (Tech Science Press))-Vol. 117, Iss: 3, pp 425-454
TL;DR: This paper makes a conclusion on image information hiding based on deep learning, which is divided into four parts of steganography algorithms, watermarking embedding algorithms, coverless information hiding algorithms and steganalysis algorithms based onDeep learning.
Abstract: With the development of data science and technology, information security has been further attention. In order to solve privacy problems such as personal privacy being peeped and copyright being infringed, information hiding technology has been developed. Image information hiding is to make use of the redundancy of the cover image to hide secret information in it. Ensure that the stego image cannot be distinguished from the cover image, and send secret information to receiver through the transmission of the stego image. At present, the model based on deep learning is also widely applied to the field of information hiding. This paper makes a conclusion on image information hiding based on deep learning. It is divided into four parts of steganography algorithms, watermarking embedding algorithms, coverless information hiding algorithms and steganalysis algorithms based on deep learning. From these four aspects, the state-of-theart information hiding technologies based on deep learning are illustrated and analyzed.
Citations
More filters
Proceedings Article•
29 Jan 2019TL;DR: The Wasserstein distance serves as a loss function for unsupervised learning which depends on the choice of a ground metric on sample space and the new formulation is more robust to the natural variability of images and provides for a more continuous discriminator in sample space.
Abstract: The Wasserstein distance serves as a loss function for unsupervised learning which depends on the choice of a ground metric on sample space. We propose to use a Wasserstein distance as the ground metric on the sample space of images. This ground metric is known as an effective distance for image retrieval, since it correlates with human perception. We derive the Wasserstein ground metric on image space and define a Riemannian Wasserstein gradient penalty to be used in the Wasserstein Generative Adversarial Network (WGAN) framework. The new gradient penalty is computed efficiently via convolutions on the L (Euclidean) gradients with negligible additional computational cost. The new formulation is more robust to the natural variability of images and provides for a more continuous discriminator in sample space.
31 citations
TL;DR: Zhang et al. as mentioned in this paper proposed a novel multiple image hiding framework based on invertible neural network, namely DeepMIH, which can be cascaded as many times as required to achieve the hiding of multiple images.
Abstract: Multiple image hiding aims to hide multiple secret images into a single cover image, and then recover all secret images perfectly. Such high-capacity hiding may easily lead to contour shadows or color distortion, which makes multiple image hiding a very challenging task. In this paper, we propose a novel multiple image hiding framework based on invertible neural network, namely DeepMIH. Specifically, we develop an invertible hiding neural network (IHNN) to innovatively model the image concealing and revealing as its forward and backward processes, making them fully coupled and reversible. The IHNN is highly flexible, which can be cascaded as many times as required to achieve the hiding of multiple images. To enhance the invisibility, we design an importance map (IM) module to guide the current image hiding based on the previous image hiding results. In addition, we find that the image hidden in the high-frequency sub-bands tends to achieve better hiding performance, and thus propose a low-frequency wavelet loss to constrain that no secret information is hidden in the low-frequency sub-bands. Experimental results show that our DeepMIH significantly outperforms other state-of-the-art methods, in terms of hiding invisibility, security and recovery accuracy on a variety of datasets.
12 citations
TL;DR: This paper explores an intelligent dynamic expansion method for text emotional lexicon based on deep learning in detail and proposes a method of text Emotional modulation steganography based on machine learning to effectively protect sensitive information.
Abstract: To effectively protect sensitive information, this paper proposes a method of text Emotional modulation steganography based on machine learning. Firstly, we explore an intelligent dynamic expansion...
10 citations
TL;DR: In this paper , the authors present a review of how digital watermarking technologies are really very helpful in the copyright protection of the DNNs and several optimizers are proposed to improve the accuracy against the fine-tuning attack.
Abstract: Nowadays, deep learning achieves higher levels of accuracy than ever before. This evolution makes deep learning crucial for applications that care for safety, like self-driving cars and helps consumers to meet most of their expectations. Further, Deep Neural Networks (DNNs) are powerful approaches that employed to solve several issues. These issues include healthcare, advertising, marketing, computer vision, speech processing, natural language processing. The DNNs have marvelous progress in these different fields, but training such DNN models requires a lot of time, a vast amount of data and in most cases a lot of computational steps. Selling such pre-trained models is a profitable business model. But, sharing them without the owner permission is a serious threat. Unfortunately, once the models are sold, they can be easily copied and redistributed. This paper first presents a review of how digital watermarking technologies are really very helpful in the copyright protection of the DNNs. Then, a comparative study between the latest techniques is presented. Also, several optimizers are proposed to improve the accuracy against the fine-tuning attack. Finally, several experiments are performed with black-box settings using several optimizers and the results are compared with the SGD optimizer.
10 citations
13 May 2019
TL;DR: It is argued that information could be hidden behind approximate computation without compromising the computation accuracy or energy efficiency.
Abstract: There are many interesting advances in approximate computing recently targeting the energy efficiency in system design and execution. The basic idea is to trade computation accuracy for power and energy during all phases of the computation, from data to algorithm and hardware implementation. In this paper, we explore how to utilize approximate computing for security based information hiding. More specifically, we will demonstrate with examples the potential of embedding information in approximate hardware and approximate data, as well as during approximate computation. We analyze both the security vulnerabilities that this may cause and the potential security applications enabled by such information hiding. We argue that information could be hidden behind approximate computation without compromising the computation accuracy or energy efficiency.
10 citations
Cites background from "A Survey of Image Information Hidin..."
...State-of-the-art can be found in survey articles such as [17]....
[...]