Chun Shan's research while affiliated with Guangdong Polytechnic Normal University and other places

Publications (63)

Preprint
Full-text available
Aiming at the problem of slow retrieval speed due to a large amount of data in person re-identification, this paper introduces Taylor expansion into a deep neural network, and obtains Taylor deep neural network for feature extraction, which is combined with the proposed hash probability coding algorithm, and get a fast retrieval algorithm for perso...
Article
Deep Neural Networks (DNNs) have developed rapidly in data privacy protection applications such as medical treatment and finance. However, DNNs require high-speed and high-memory computers in terms of computation, otherwise training can be very lengthy. Furthermore, DNNs are often not available in resource-constrained mobile devices. Therefore, tra...
Article
A 6G network is not only faster, but also offers a wider range of services than 5G networks, which will lead to an increased number of participants. However, combined with the Internet of Everything, 6G networks face security issues such as man-in-the-middle hijacking and bypass listening. Because covert transmission is inherently highly concealed...
Article
Full-text available
In wireless blockchain network (WBN), it is necessary to study the impact of delay performance on blockchain technology with different data rates, because the throughput performance is not the only goal. We propose an analysis model to evaluate network performance based on both delay performance and network performance. Firstly, we separate the com...
Article
Full-text available
To evade security detection, hackers always add a deceptive packer outside of the original malicious codes. The coexistence of original unpacked samples and packed samples of same family needs special attention in malware detection. The features of packed malware are changed by the packer, which would disturb the prediction results of malware class...
Article
In recent years, the evolving Internet of Things(IoT) technology has been widely used in various industrial scenarios, whereby massive sensor data involving both normal data and anomalous data are generated. However, the anomalies involved might have a great impact on the industrial sustainability. Actually, in most scenarios, it is of vital import...
Article
Network service, as a behavioral process oriented toward network operation, plays a vital role in the function of network application system. State-of-the-art researches are prone to ignore the intrinsic behavioral characteristics of network services, and yield subjective and biased analysis results on service selection, coordination, composition,...
Article
B5G aims to meet the demands of today's growing mobile traffic and expand the communication space. Considering that the intelligent application to B5G wireless communications will involve the security issues of user data and operational data, in this paper, the maximum capacity problem of the multi-watermarking method in multimedia signal hiding is...
Article
Multimedia information (e.g., photos) is subject to numerous attacks when extensively dispersed, excellent stealth and robustness play a critical role in information concealment. Next, to further improve the imperceptibility of the generated images, we introduce an information embedding based on feature extraction, since the feature points themselv...
Preprint
Full-text available
Computational task offloading based on edge computing can deal with the performance bottleneck faced by traditional cloud-based systems for industrial Internet of things (IIoT). To further optimize computing efficiency and resource allocation, collaborative offloading has been put forward to enable the offloading from edge devices to IIoT terminal...
Article
Visible Light Communication (VLC) is an emerging short-range optical communication technology that can alleviate spectrum congestion. However, VLC faces security problems with man-in-the-middle hijacking and bypass listening. Since the covert transmission of visible light information has the characteristics of strong concealment and difficult detec...
Article
6G networks can flexibly arrange network resources in multiple areas through integration with edge computing and cloud computing. However, devices at the edge of the network generate large quantities of multimodal data (e.g., user behaviour records, audio, and video), creating new challenges for data security and privacy, which has led to research...
Article
Calculating system damage caused by a cyberattack can help in understanding the impact and destructiveness of the attack to discover system security weaknesses. Thus, system damage calculations is important in the process of network offense-defense confrontation. However, there is little research on attack damage calculation. Current methods are un...
Article
The means to achieve DDoS (distributed denial of service) attacks are becoming increasingly automated and diverse. A problem that automated attack tools cannot address, at least for now, is the inevitable repetitive or periodic nature of traffic data, which are important features for the effective detection of DDoS attacks. Some researchers have pr...
Article
Nowadays, a large number of civilian unmanned aerial vehicles (UAVs) are increasingly being used in many of our daily applications. However, there are many kinds of UAVs that need to enhance their endurance due to their limited resources. In order to make the UAVs operate efficiently, it is necessary to schedule UAVs with charging requirements. In...
Article
Full-text available
With the rapid development of Internet of Things (IoT), massive sensor data are being generated by the sensors deployed everywhere at an unprecedented rate. As the number of Internet of Things devices is estimated to grow to 25 billion by 2021, when facing the explicit or implicit anomalies in the real-time sensor data collected from Internet of Th...
Article
Full-text available
Texture classification plays an important role for various computer vision tasks. Depending upon the powerful feature extraction capability, convolutional neural network (CNN)-based texture classification methods have attracted extensive attention. However, there still exist many challenges, such as the extraction of multilevel texture features and...
Article
Full-text available
This paper proposes a new structural design to excite surface plasmonic polaritons to enhance the double-ring interference structure. The double-ring structure was etched into a thin film to form fundamental interference patterns, and periodic concentric-ring grooves were employed to gather energy from the surrounding regions through the excitation...
Article
Full-text available
Malware threats and privacy protection are two of the biggest challenges in the cloud computing environment. Many studies have focused on the accuracy of malware detection, but they did not sufficiently take into account the privacy protection of cloud tenants. This paper proposes a novel malware detection model, based on semi-supervised transfer l...
Article
Because of the sequence and number of calls of functions, software network cannot reflect the real execution of software. Thus, to detect crucial functions (DCF) based on software network is controversial. To address this issue, from the viewpoint of software dynamic execution, a novel approach to DCF is proposed in this paper. It firstly models, t...
Article
Full-text available
With the rapid development of networks, network security is a serious problem. To evaluate a network accurately, this paper proposes a network risk evaluation method based on a differential manifold (DM) and research on traditional methods. The DM divides the network risk evaluation into network structure risk and network behavior risk evaluations....
Article
Full-text available
The weighted traversal pattern is important in software system for a better understanding of the internal structure and behavior of software. To mine important patterns of software, a complex network‐based Optimal Software Fault Patterns Miner is presented. By analyzing the multiple execution traces of software and the relations among functions, we...
Chapter
Complex software system will bring a lot of software security problems, it is very meaningful to know how to more accurately abstract the software network model from the software system and efficiently find the key nodes in the software network. This research takes open source software as the research object, constructs a directed network model of...
Article
Full-text available
In recent years, advanced threat attacks are increasing, but the traditional network intrusion detection system based on feature filtering has some drawbacks which make it difficult to find new attacks in time. This paper takes NSL-KDD data set as the research object, analyses the latest progress and existing problems in the field of intrusion dete...
Article
Full-text available
Device to Device (D2D) communication is a key technology in 5th generation wireless systems to increase communication capacity and spectral efficiency. Applying caching into D2D communication networks, the device can retrieve content from other devices by establishing D2D communication links. In this way, the backhaul traffic can be significantly r...
Article
In a software network system, it is of great significance to identify key functions for software fault detection and maintenance. In order to better understand the characteristics and internal structure of software, a key Node Discovery algorithm based on Evidence Theory called NDET is proposed in this paper. First, the software complex network mod...
Preprint
Full-text available
To build a secure communications software, Vulnerability Prediction Models (VPMs) are used to predict vulnerable software modules in the software system before software security testing. At present many software security metrics have been proposed to design a VPM. In this paper, we predict vulnerable classes in a software system by establishing the...
Article
The function and quality of software is closely linked to its structure. One of the ways to study the structural features of software is the idea of applying complex networks. Software is abstracted into various network models for the purpose of study. Eigenvalues and additional parameters are then extracted from the model. Analyzing the characteri...
Chapter
Outsourcing heavy storage and computation to the cloud servers now becomes more and more popular. How to secure share the cloud storage is an important problem for many mobile users. Proxy re-encryption is such a cryptographic primitive which can be used to secure share cloud data. Until now there are many kinds of proxy re-encryption schemes with...
Chapter
Proxy re-encryption acts an important role in secure data sharing in cloud storage. There are many variants of proxy re-encryption until now, in this paper we focus on the timed-realise conditional proxy broadcast re-encryption. In this primitive, if and only the condition and time satisfied the requirement, the proxy can re-encrypt the delegator(b...
Chapter
In order to enhance the security of network operations, establish effective security measures, prevent the destruction of security incidents, and reduce or eliminate the losses caused by threats through network risk assessment is of important practical significance. However, most risk assessment methods focus on the research of threats and vulnerab...
Article
Full-text available
Fuzzing is regarded as the most promising method for protocol vulnerabilities discovering in network security of Internet of Things (IoT). However, one fatal drawback of existing fuzzing methods is that a huge number of test files are required to maintain a high test coverage. In this paper, a novel method based on protocol reverse engineering is p...
Article
The analysis of software system evolution is highly significant in software research as the evolution runs throughout the lifecycle of a software system. Considering a software system as an algebraic engineering system, we propose a software system evolution analysis method based on algebraic topology. First, from a complex network perspective, we...
Article
Information Centric Networking (ICN) is a novel future network architecture that is focusing on content distribution. Its ubiquitous caching schemes can improve network performance. In this paper, we propose a node importance to community based caching scheme with network coding in ICN, which is named as NICNC. For each community, content router ma...
Article
During the prediction of software defect distribution, the data redundancy caused by the multi-dimensional measurement will lead to the decrease of prediction accuracy. In order to solve this problem, this paper proposed a novel software defect prediction model based on neighborhood preserving embedded support vector machine (NPE-SVM) algorithm. Th...
Article
Full-text available
A network security metric may provide quantifiable evidence to assist security practitioners in securing computer networks. However, research on security metrics based on attack graph is not applicable to the characteristics of internal attack; therefore we propose an internal network security metric method based on attack probability. Our approach...
Article
Full-text available
Identifying influential nodes is important for software in terms of understanding the design patterns and controlling the development and the maintenance process. However, there are no efficient methods to discover them so far. Based on the invoking dependency relationships between the nodes, this paper proposes a novel approach to define the node...
Chapter
The limited storage capacity of small devices, such as mobile phone, has become a bottleneck for the development of many application, especially for security applications. The Ciphertext Policy Attributes Based-Encryption (CP-ABE) is a promising cryptographic scheme that allows encryption to choose an access structure that protects sensitive data....
Chapter
Under the settings of cloud storage, user’s private data is distributed and sent to different servers for storage service, thus authentication systems are required to ensure data integrity. In this paper, combining the idea of Dario Catalanno’s arithmetic circuit with Rank-based Merkle Hash Tree structure, a novel homomorphic authentication scheme...
Article
Due to the rapid rise of automated tools, the number of malware variants has increased dramatically, which poses a tremendous threat to the security of the Internet. Recently, some methods for quick analysis of malware have been proposed, but these methods usually require a large computational overhead and can not classify samples accurately for la...
Conference Paper
The research on classification method of malicious code is helpful for researchers to understand attack characteristics quickly, and help to reduce the loss of users and even the states. Currently, most of the malware classification methods are based on supervised learning algorithms, but it is powerless for the small number of labeled samples. The...
Conference Paper
Internet worms pose a serious threat to the Internet security. In order to avoid the security detection and adapt to diverse target environment, the attackers often modify the existing worm code, then get the variants of original worm. Therefore, it is of practical significance to determine the cognate relationship between worms quickly and accurat...
Conference Paper
Vulnerability Prediction Models (VPMs) are used to predict vulnerability-prone modules and now many software security metrics have been proposed. In this paper, we predict vulnerability-prone components. Based on software network graph we define component cohesion and coupling metrics which are used as security metrics to build the VPM. To validate...
Article
Full-text available
It is extremely important for the study of software behavior modeling for software security research. This article determines whether the security of software operation by analyzing the credibility of software behavior, monitoring software running status. This paper focuses on a modeling algorithm, namely the GK-tail algorithm, which based on softw...
Conference Paper
Array bounds is the most commonly fault in java programs design, it often leads to wrong results even system crash. To solve these problems, this paper proposed a detecting array bounds method based on symbolic execution. The method generated the abstract syntax tree from the source code, and then created a control flow graph according to the abstr...
Conference Paper
Fuzzing has become one of the most important technologies in the field of network security, and fuzzer also has become an important tool for discovering network vulnerabilities. But for the stateful network protocol fuzzing, most of fuzzers could not effectively cover the state trajectory, and not achieve a good automation. Aiming at the above issu...
Article
Static analysis can be classified into intra-procedural analysis and inter-procedural analysis-by-analysis objects. Inter-procedural analysis need to analyze the whole program adopting bottom-up parsing algorithms. Inter-procedural analysis can be converted to intra-procedural analysis by logging the context of follower’s function call in bottom-up...
Conference Paper
The software components is discussed and component-oriented software development is shown in the paper. A group of game engine component is developed, and two games are produced by game engines. Then the quality control and management of components and software are discussed in this paper. The system of evaluating software quality is developed and...
Conference Paper
Document examination and approval system is a typical workflow system. Based on real OA (Office Automation) system, the Petri net modeling workflow is discussed in this paper. Three typical procedures are modeled by Petri net, which are delivering the document management, receiving the document management, and multi-level document examination and a...
Conference Paper
A recent study namely software defect prediction model based on Local Linear Embedding and Support Vector Machines (LLE-SVM) has indicated that Support Vector Regression (SVR) has an interesting potential in the field of software defect prediction. However, the parameters optimization of LLE-SVM model is computationally expensive by using the grid...
Article
Communication between heterogeneous systems is difficult to be achieved without affecting the existing systems in Enterprise Application Integration. A kind of dynamic web services publishing software based on CXF is proposed in this paper. The purpose of this software are twofold. Firstly, it encapsulates specified data called by other systems int...
Article
The issue on finding an effective evaluation method on software structural stability is rarely touched upon in software security research. An assessment method of software microstructural stability was developed by Khalil in 2002. A new evaluation method on software structural stability is proposed in this paper, which is based on Motifs according...
Article
The coordination modeling language Paradigm addresses collaboration between components in terms of dynamic constraints. The consistency rule is a key notion in Paradigm. However, the original process of visualization modeling is without consistency rule, leading to complex. For this reason, by analyzing the theory of modeling in Paradigm and gettin...
Article
Software defect prediction strives to improve software security by helping testers locate the software defects accurately. The data redundancy caused by the overmuch attributes in defects data set will make the prediction accuracy decrease. A model based on locally linear embedding and support vector machine (LLE-SVM) is proposed to solve this prob...
Article
Aiming at the test data generation, which is one of the key issues in the network protocol fuzzing, this paper presents a new method on the basis of classification tree and heuristic operator. The method firstly builds up a protocol classification tree divided into 4 layers: target network protocol, protocol fields, attributes belonging to all fiel...

Citations

... Recently, machine learning techniques have been proposed in the literature for intrusion detection in IoMT networks [16][17][18] and other technology fields [19]. The authors in [20] surveyed the security and privacy solutions in IoMT and discussed various solutions, including machine learning solutions to solve the attack detection problem. ...
... In recent years, with the successful application of neural networks in many fields, person reidentification based on neural networks has received more and more attention. In the current neural network [21,22], it can also learn representation learning and metric learning while extracting high-dimensional features. Ahmed et al. [23] handles person images by designing two novel layers to capture the relationship between two views: a cross-input neighborhood disparity layer, and a subsequent layer that summarizes these disparities. ...
... In recent years, with the successful application of neural networks in many fields, person reidentification based on neural networks has received more and more attention. In the current neural network [21,22], it can also learn representation learning and metric learning while extracting high-dimensional features. Ahmed et al. [23] handles person images by designing two novel layers to capture the relationship between two views: a cross-input neighborhood disparity layer, and a subsequent layer that summarizes these disparities. ...
... GRUs have been shown to be able to achieve comparable performance as LSTM in several applications, such as speech recognition, traffic load prediction, etc., with lower computational complexity [49][50][51]. 8 ...
... Due to the traffic/congestion control mechanism of protocols and RTT (Round-Trip delay Time) in TCP protocol, the network traffic consists of various periodic components [16]. Additionally, it has been reported in many studies that DDoS attack traffic has a periodic characteristic [17,18,19,20] and therefore, this periodicity information traffic can be used for discriminating the DDoS attack traffic from the normal one. To the best of our knowledge, the most powerful tool to analyze the periodic components is the frequency-domain analysis [21]. ...
... Many algorithms have been proposed for scheduling problems based on different methods, including queueing-based methods, e.g., [11,26], optimization-based methods, e.g., [10,13], dynamic programming (DP)-based algorithms, e.g., [3,28], and Lyapunov control-based approaches, e.g., [16,23]. However, these approaches either require prior knowledge about system dynamics, or suffer from curse-of-dimensionality due to large state space, or focus on stability constraints rather than delay. ...
... (v) Study [4] presents that in edge computing environments, a dynamic network failure happens frequently due to factors like time-varying nodes and service fluctuations. is failure often affects the performance of applications or even causes crashes. ...
... Shannon entropy was evaluated to consider both the randomness of the application programming interface (API) and printable string information (PSI) features [8], [9]. Moreover, behavioral features such as key modification, file operations regarding the registry and network activities for malware detection [9]- [11]. The features are combined and summed up for training the feature set emerged with the machine learning-based algorithms for malware classification [11]- [13]. ...
... A comparative analysis with the existing methods shows an improvement with all the datasets under consideration. In [24], an improvised local linear embedded support vector machine algorithm provides better prediction of defects when compared to support vector machine and local linear embedding support vector machine algorithm. The drawback of local linear embedding support vector machine algorithm where it neglects the class imbalance is overcome by the author's proposed improvised algorithm. ...
... Another ensemble-based approach aiming for higher accuracies was proposed by X. Gao et al. [13], which considers a static dataset by applying several tree-based classifiers in cooperation. Liang and Ma [14] recently mentioned the detection rates of IDSs gradually decaying with the emergence of new attacks, which they address by downloading the latest database and retraining the whole model without previous knowledge. ...