Xiaoyuan Yang

Bio: Xiaoyuan Yang is an academic researcher. The author has contributed to research in topics: Steganography & Information hiding. The author has an hindex of 9, co-authored 24 publications receiving 167 citations.

Recent Advances of Image Steganography with Generative Adversarial Networks

Abstract: In the past few years, the Generative Adversarial Network (GAN), which proposed in 2014, has achieved great success. There have been increasing research achievements based on GAN in the field of computer vision and natural language processing. Image steganography is an information security technique aiming at hiding secret messages in common digital images for covert communication. Recently, research on image steganography has demonstrated great potential by introducing GAN and other neural network techniques. In this paper, we review the art of steganography with GANs according to the different strategies in data hiding, which are cover modification, cover selection, and cover synthesis. We discuss the characteristics of the three strategies of GAN-based steganography and analyze their evaluation metrics. Finally, some existing problems of image steganography with GAN are summarized and discussed. Potential future research topics are also forecasted.

Fully Homomorphic Encryption Encapsulated Difference Expansion for Reversible Data Hiding in Encrypted Domain

Abstract: This paper proposes a fully homomorphic encryption encapsulated difference expansion (FHEE-DE) scheme for reversible data hiding in encrypted domain (RDH-ED). The homomorphic circuits and ciphertext operations are elaborated. Key-switching and bootstrapping techniques are introduced to control the ciphertext extension and decryption failure of homomorphic encryption. A key-switching based least-significant-bit (KS-LSB) data hiding method has been designed to realize data extraction directly from the encrypted domain without the private key. In application, the user first encrypts the plaintext and uploads ciphertext to the server. The server embeds additional data into the ciphertext by performing FHEE-DE data hiding and KS-LSB data hiding. Additional data can be extracted directly from the marked ciphertext by the server without the private key. The user owns the private key and can decrypt the marked ciphertext to obtain the marked plaintext. Then additional data or plaintext can be obtained from the marked plaintext by using the standard DE extraction or recovery. The server could also implement FHEE-DE recovery or extraction on the marked ciphertext to return the ciphertext of original plaintext or additional data to the user. Experimental results demonstrate that the embedding capacity and reversibility of the proposed scheme are superior to existing RDH-ED methods, and fully separability is achieved without reducing the security of encryption.

Generative Steganography by Sampling

Abstract: In this paper, a novel data-driven information hiding scheme called “generative steganography by sampling” (GSS) is proposed. Unlike in traditional modification-based steganography, in our method the stego image is directly sampled by a powerful generator: no explicit cover is used. Both parties share a secret key used for message embedding and extraction. The Jensen-Shannon divergence is introduced as a new criterion for evaluating the security of generative steganography. Based on these principles, we propose a simple practical generative steganography method that uses semantic image inpainting. The message is written in advance to an uncorrupted region that needs to be retained in the corrupted image. Then, the corrupted image with the secret message is fed into a Generator trained by a generative adversarial network (GAN) for semantic completion. Message loss and prior loss terms are proposed for penalizing message extraction error and unrealistic stego image. In our design, we first train a generator whose training target is the generation of new data samples from the same distribution as that of existing training data. Next, for the trained generator, backpropagation to the message and prior loss are introduced to optimize the coding of the input noise data for the generator. The presented experiments demonstrate the potential of the proposed framework based on both qualitative and quantitative evaluations of the generated stego images.

A New Multi-class SVM Algorithm Based on One-Class SVM

Abstract: Multi-class classification is an important and on-going research subject in machine learning and data mining. In this paper, we propose a new support vector algorithm, called OC-K-SVM, for multi-class classification based on one-class SVM. For k-class problem, this method constructs k classifiers, where each one is trained on data from one class. OC-K-SVM has parameters that enable us to control the number of support vectors and margin errors effectively, which is helpful in improving the accuracy of each classifier. We give some theoretical results concerning the significance of the parameters and show the robustness of classifiers. In addition, we have examined the proposed algorithm on several benchmark data sets, and our preliminary experiments confirm our theoretical conclusions.

Generative Steganography with Kerckhoffs' Principle based on Generative Adversarial Networks.

Abstract: The distortion in steganography comes from the modification or recoding on the cover image during the embedding process. The changes of the cover always leave the steganalyzer with possibility of discriminating. Therefore, we propose to use a cover to send out secret messages without any modification by training the cover image to generate the secret messages. To ensure the security of such a generative scheme, we require the generator to meet Kerckhoffs' principle. Based on above proposal, we propose generative steganography with Kerckhoffs' principle (GSK) in this letter. In GSK, we use a generator based on generative adversarial networks (GAN) to output the secret messages if and only if the data-hiding key and the cover image are both inputted. Without the data-hiding key or the cover image, only meaningless results would be outputted. We detail the framework and the internal structure of GSK. In our training procedures, there are two GANs, Key-GAN and Cover-GAN, designed to work jointly making the generated results under the control of the data-hiding key and the cover image. Experimental results concentrate on the training process and the working performance of GSK which demonstrate that GSK can use any image to realize steganography with Kerckhoffs' principle without any modification.

VAE-Stega: Linguistic Steganography Based on Variational Auto-Encoder

Abstract: In recent years, linguistic steganography based on text auto-generation technology has been greatly developed, which is considered to be a very promising but also a very challenging research topic. Previous works mainly focus on optimizing the language model and conditional probability coding methods, aiming at generating steganographic sentences with better quality. In this paper, we first report some of our latest experimental findings, which seem to indicate that the quality of the generated steganographic text cannot fully guarantee its steganographic security, and even has a prominent perceptual-imperceptibility and statistical-imperceptibility conflict effect (Psic Effect). To further improve the imperceptibility and security of generated steganographic texts, in this paper, we propose a new linguistic steganography based on Variational Auto-Encoder (VAE), which can be called VAE-Stega. We use the encoder in VAE-Stega to learn the overall statistical distribution characteristics of a large number of normal texts, and then use the decoder in VAE-Stega to generate steganographic sentences which conform to both of the statistical language model as well as the overall statistical distribution of normal sentences, so as to guarantee both the perceptual-imperceptibility and statistical-imperceptibility of the generated steganographic texts at the same time. We design several experiments to test the proposed method. Experimental results show that the proposed model can greatly improve the imperceptibility of the generated steganographic sentences and thus achieves the state of the art performance.

Chinese Remaindering with Errors

Abstract: The Chinese remainder theorem states that a positive integer m is uniquely specified by its remainder module k relatively prime integers p/sub 1/, /spl middot//spl middot//spl middot/, p/sub k/, provided m

Image Steganography: A Review of the Recent Advances

Abstract: Image Steganography is the process of hiding information which can be text, image or video inside a cover image. The secret information is hidden in a way that it not visible to the human eyes. Deep learning technology, which has emerged as a powerful tool in various applications including image steganography, has received increased attention recently. The main goal of this paper is to explore and discuss various deep learning methods available in image steganography field. Deep learning techniques used for image steganography can be broadly divided into three categories - traditional methods, Convolutional Neural Network-based and General Adversarial Network-based methods. Along with the methodology, an elaborate summary on the datasets used, experimental set-ups considered and the evaluation metrics commonly used are described in this paper. A table summarizing all the details are also provided for easy reference. This paper aims to help the fellow researchers by compiling the current trends, challenges and some future direction in this field.

Secure Reversible Image Data Hiding Over Encrypted Domain via Key Modulation

Abstract: This paper proposes a novel reversible picture information concealing plan over encoded area. Information inserting is accomplished through an open key balance system, in which access to the mystery encryption key isn't required. At the decoder side, an effective two-class SVM classifier is intended to recognize scrambled and non encoded picture patches, enabling us to mutually translate the installed message and the first picture flag. Contrasted and the best in class strategies, the proposed approach gives higher inserting limit and can consummately remake the first picture and also the implanted message. Broad exploratory outcomes are given to approve the prevalent execution of our plan.