Min-qing Zhang

Bio: Min-qing Zhang is an academic researcher. The author has contributed to research in topics: Information hiding & Steganography. The author has an hindex of 3, co-authored 5 publications receiving 44 citations.

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.

Ciphertext domain multi-bit reversible information hiding method

Abstract: The invention provides a ciphertext domain multi-bit reversible information hiding method capable of effectively ensuring large volume embedment of data, reversible recovery of carrier data and undetectability of embedded information on the premise of meeting separable steganography The method comprises the following steps: 1, parameter setting and data pre-processing; 2, encryption and information embedment; and 3, decryption and information extraction By recoding ciphertext data based on an R-LWE (Ring Learning with Errors) public key cipher algorithm, a user can embed multi-ary information based on ciphertext domain operation to realize data encryption After the information is embedded, the user can effectively extract the hidden information with a steganographic key and recover the data before encryption without errors by using a decryption key Compared with the existing ciphertext domain steganography, the method has the advantages that error-free decryption of the embedded ciphertext and effective extraction of the hidden information can be realized, and the decryption and extraction processes are separable

Generative Steganography Based on GANs

Abstract: Traditional steganography algorithms embed secret information by modifying the content of the images, which makes it difficult to fundamentally resist the detection of statistically based steganalysis algorithms. To solve this problem, we propose a novel generative steganography method based on generative adversarial networks. First, we represent the class labels of generative adversarial networks in binary code. Second, we encode the secret information into binary code. Then, we replace the labels with the secret information as the driver to generate the encrypted image for transmission. Finally, we use the auxiliary classifier to extract the label of the encrypted image and obtain the secret information through decoding. Experimental results and analysis show that our method ensures good performance in terms of steganographic capacity, anti-steganalysis and security.

Recognizing human actions using bag-of-features and Intersection Kernel Support Vector Machines

Abstract: This paper addresses the problem of human action recognition by introducing a new representation of image sequences as a collection of spatio-temporal events that are localized at interest point. The interest points are detected by the SIFT detector and a spatio-temporal interest point detector. We proposed a new bag of words approach to represent videos in two different models. Intersection Kernel Support Vector Machines is used for classification. We also present action classification results on two different datasets. Our results are either comparable to previous published results on these datasets.

A mishmash of methods for mitigating the model mismatch mess

Abstract: The model mismatch problem occurs in steganalysis when a binary classifier is trained on objects from one cover source and tested on another: an example of domain adaptation. It is highly realistic because a steganalyst would rarely have access to much or any training data from their opponent, and its consequences can be devastating to classifier accuracy. This paper presents an in-depth study of one particular instance of model mismatch, in a set of images from Flickr using one fixed steganography and steganalysis method, attempting to separate different effects of mismatch in feature space and find methods of mitigation where possible. We also propose new benchmarks for accuracy, which are more appropriate than mean error rates when there are multiple actors and multiple images, and consider the case of 3-valued detectors which also output `don't know'. This pilot study demonstrates that some simple feature-centering and ensemble methods can reduce the mismatch penalty considerably, but not completely remove it.

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.

Machine Learning and Deep Learning Based Traffic Classification and Prediction in Software Defined Networking

Abstract: The Internet is constantly growing in size and becoming more complex. The field of networking is thus continuously progressing to cope with this monumental growth of network traffic. While approaches such as Software Defined Networking (SDN) can provide a centralized control mechanism for network traffic measurement, control, and prediction, still the amount of data received by the SDN controller is huge. To process that data, it has recently been suggested to use Machine Learning (ML). In this paper, we review existing proposal for using ML in an SDN context for traffic measurement (specifically, classification) and traffic prediction. We will especially focus on approaches that use Deep learning (DL) in traffic prediction, which seems to have been mostly untapped by existing surveys. Furthermore, we discuss remaining challenges and suggest future research directions.

Privacy protection for fog computing and the internet of things data based on blockchain

Abstract: With the development of the Internet of Things (IoT) field, more and more data are generated by IoT devices and transferred over the network. However, a large amount of IoT data is sensitive, and the leakage of such data is a privacy breach. The security of sensitive IoT data is a big issue, as the data is shared over an insecure network channel. Current solutions include symmetric encryption and access controls to secure the data transfer, but they have some drawbacks such as a single point of failure. Blockchain is a promising distributed ledger technology that can prevent the malicious tampering of data, offering reliable data storage. This paper proposes a distributed access control system based on blockchain technology to secure IoT data. The proposed mechanism is based on fog computing and the concept of the alliance chain. This method uses mixed linear and nonlinear spatiotemporal chaotic systems (MLNCML) and the least significant bit (LSB) to encrypt the IoT data on an edge node and then upload the encrypted data to the cloud. The proposed mechanism can solve the problem of a single point of failure of access control by providing the dynamic and fine-grained access control for IoT data. The experimental results of this method demonstrated that it can protect the privacy of IoT data efficiently.