����Ŀ¼

15 February 2020, Volume 6 Issue 1

Previous Issue    Next Issue

Perspective

Construction of academic discipline of science and engineering and orientation for their ranking under the new situation

Fenghua LI,Hui LI

2020, 6(1):  1-10.  doi:10.11959/j.issn.2096-109x.2020014

Asbtract ( 246 )   HTML ( 40)   PDF (659KB) ( 221 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

At present,the key to the innovative development of our country is to improve the ability of independent innovation.The fundamental task of universities is to cultivate innovative talents who can lead the innovative development.Discipline ranking is the baton of university construction.In fact,all aspects of the work of discipline construction are carried out around discipline ranking and essentially around discipline ranking index system.The existed specific measures of discipline construction can not fully meet the requirements of the state for the construction of universities.As long as set up a reasonable discipline ranking index system,can truly promote the reform of discipline construction in universities,and fully implement the requirements of state to break the “four only” and“five only” phenomenon.Therefore,in view of the connotation of discipline construction with talent cultivating as the core,suggestions for the reform of discipline ranking index system in terms of the level of teachers,the quality of talent cultivating and the level of scientific research were proposed.

Comprehensive Review

Survey of network-layer anonymous communication protocols

Liangmin WANG,Xiaoling NI,Hui ZHAO

2020, 6(1):  11-26.  doi:10.11959/j.issn.2096-109x.2020006

Asbtract ( 656 )   HTML ( 84)   PDF (1670KB) ( 1229 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

An anonymous communication system is an overlay network built on the application layer and combining various privacy protection technologies such as data forwarding,content encryption,and traffic obfuscation to hide communication relationships between entities and forwarded contents.However,there is a deficiency in the balance between performance and security as an anonymous communication system operating over an overlay network.With the advance of the future internet architectures,it is possible to build an infrastructure-based anonymous communication system.Such anonymous communication systems design anonymity as network infrastructure services and provide encryption operations for routers,which can solve the part problem of scalability and performance limitations of anonymous network.They can also be called network-layer anonymous communication protocols.The existing network-layer anonymous communication protocols (LAP,Dovetail,Hornet,PHI and Taranet) were studied.The classification standard of network-layer anonymous communication protocols were introduced.Its innovation point and specific encryption ideas were briefly described,and how to keep balance between security and performance was analyzed.The shortcomings and advantages of these kinds of network anonymous communication protocols were also pointed out.Finally,the challenges faced in the development of anonymous communication systems and the problems that need to be studied in depth were proposed.

Papers

CAN bus flood attack detection based on communication characteristics

Yimu JI,Zhipeng JIAO,Shangdong LIU,Fei WU,Jing SUN,Na WANG,Zhiyu CHEN,Qiang BI,Penghao TIAN

2020, 6(1):  27-37.  doi:10.11959/j.issn.2096-109x.2020005

Asbtract ( 607 )   HTML ( 55)   PDF (1075KB) ( 544 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

CAN has become the most extensive fieldbus for contemporary automotive applications due to its outstanding reliability and flexibility.However,the standard CAN protocol does not provide sufficient security measures and is vulnerable to eavesdropping,replay,flooding,and denial of service attacks.In order to effectively detect whether the CAN bus is attacked,and to filter malicious messages when subjected to flooding attacks.The characteristics of vehicle CAN bus message communication were analyzed,and an intrusion detection method was proposed,which could effectively perform intrusion detection and malicious message filtering.Through experimental verification,the method can detect whether the CAN bus is attacked by 100%,and the accuracy of malicious packet filtering can reach over 99%.

Adversarial examples detection method based on boundary values invariants

Fei YAN,Minglun ZHANG,Liqiang ZHANG

2020, 6(1):  38-45.  doi:10.11959/j.issn.2096-109x.2020012

Asbtract ( 383 )   HTML ( 49)   PDF (920KB) ( 723 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Nowadays,deep learning has become one of the most widely studied and applied technologies in the computer field.Deep neural networks(DNNs) have achieved greatly noticeable success in many applications such as image recognition,speech,self-driving and text translation.However,deep neural networks are vulnerable to adversarial examples that are generated by perturbing correctly classified inputs to cause DNN modes to misbehave.A boundary check method based on traditional programs by fitting the distribution to find the invariants in the deep neural network was proposed and it use the invariants to detect adversarial examples.The selection of training sets was irrelevant to adversarial examples.The experiment results show that proposed method can effectively detect the current adversarial example attacks on LeNet,vgg19 model,Mnist,Cifar10 dataset,and has a low false positive rate.

Privacy protection scheme for internet of vehicles based on homomorphic encryption and block chain technology

Ruijin WANG,Yucheng TANG,Weiqi ZHANG,Fengli ZHANG

2020, 6(1):  46-53.  doi:10.11959/j.issn.2096-109x.2020011

Asbtract ( 928 )   HTML ( 175)   PDF (1072KB) ( 1136 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In order to solve the problem that the security of traditional internet of vehicles devices is relatively low,which may threaten the privacy of users,a privacy protection scheme based on homomorphic encryption and block chain technology was proposed.This scheme added the authentication service composed of two level nodes to the proposed model to realize the permission control of roles in the model.In order to record the information of the internet of vehicles devices,a new block data structure based on homomorphic encryption (HEBDS) was proposed,which enabled the privacy data to be written into the block after being processed by the Paillier encryption algorithm,and then written into the blockchain network by the gateway node obtaining the accounting right.This scheme realized the data processing in ciphertext state,and made up for the shortage of all data disclosure in blockchain network.Through the analysis of the security of the scheme,it is proved that the scheme has the characteristics of unforgeability and privacy data security.Through homomorphic encryption of privacy data and upload to blockchain network,the scheme can distribute,share and calculate privacy data in ciphertext state,which can protect customer privacy more effectively than traditional internet of vehicles model.

Attention-based approach of detecting spam in social networks

Qiang QU,Hongtao YU,Ruiyang HUANG

2020, 6(1):  54-61.  doi:10.11959/j.issn.2096-109x.2020002

Asbtract ( 290 )   HTML ( 35)   PDF (917KB) ( 411 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In social networks,a large amount of spam has seriously threaten users' information security and the credit system of social websites.Aiming at the noise and sparsity problems,an attention-based CNN method was proposed to detect spam.On the basis of classical CNN,this method added a filter layer in which an attention mechanism based on Naive Bayesian weighting technology was designed to solve the noise issue.What’s more,instead of the original pooling strategy,it adapted an attention-based pooling policy to alleviate the sparsity problem.Compared with other methods,the results show that the accuracy has increased by 1.32%，2.15%，0.07%，1.63% on four different data sets.

Research on the method of discovering specific organization structure in bank account transaction network

Fang LYU,Xijing LU,Wei WANG,Junheng HUANG,Bailing WANG

2020, 6(1):  62-69.  doi:10.11959/j.issn.2096-109x.2020001

Asbtract ( 215 )   HTML ( 18)   PDF (869KB) ( 128 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In recent years,stakeholder economic crime behaviors such as illegal pyramid schemes,illegal fund raising and money laundering despite repeated prohibitions,makes the research of anomaly detection in financial transaction network has gradually attracted the attention of researchers.The way how to fund flow between bank accounts in an illegal organization implies the relationship structure of their members.Firstly,a directed weighted transaction network model was built on the basis of the transaction characteristics.Then,combining with the localtopology structure of the built transaction network of the accounts,two kinds of core nodes of the organization,including black hole nodes and star nodes,were defined.By analyzing the relationship between those two kinds nodes,an organization discovery algorithm of combining “black hole and star nodes” based on spanning subgraph was proposed.Experiments on real bank accounts transaction network containing illegal pyramid scheme organizations show the effectiveness of the algorithm in discovering the specific tree organization structure.

Software-defined protocol independent parser based on FPGA

Lixin MIAO,Qinrang LIU,Xin WANG

2020, 6(1):  70-76.  doi:10.11959/j.issn.2096-109x.2020013

Asbtract ( 217 )   HTML ( 18)   PDF (1246KB) ( 433 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the boom of information technology,heterogeneous networks with various functions emerge in endlessly,heterogeneous fusion network has become the inevitable trend of the development of the next generation network.To realize communication between heterogeneous networks,network forwarding equipment is essential.Traditional forwarding devices only support fixed protocol configuration and lack scalability,so they cannot support new network protocols.In view of this situation,a software defined protocol independent parser based on FPGA was proposed.The software defined the parsing process,giving the parser flexible and programmable features.It can analyze multiple protocol packets and extract key information needed for protocol conversion without changing hardware devices.The parser through a high-performance FPGA platform were implemented and hardware resource overhead and performance were evaluated.Experimental results show that it can complete the fast parsing of various heterogeneous network protocols and obtain complete analytical data.

Scheme for identifying malware traffic with TLS data based on machine learning

Ziming LUO,Shubin XU,Xiaodong LIU

2020, 6(1):  77-83.  doi:10.11959/j.issn.2096-109x.2020008

Asbtract ( 1205 )   HTML ( 189)   PDF (1057KB) ( 2997 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Based on analyzing the characteristics of transport layer security (TLS) protocol,a distributed automation malicious traffic detecting system based on machine learning was designed.The characteristics of encrypted malware traffic from TLS data,observable metadata and contextual flow data was extracted.Support vector machine,random forest and extreme gradient boosting were used to compare the performance of the mainstream malicious encryption traffic identification which realized the efficient detection of malicious encryption traffic,and verified the validity of the detection system of malicious encryption traffic.

Video inter-frame tampering detection algorithm fusing multiple features

Hui XIAO,Bin WENG,Tianqiang HUANG,Han PU,Zehui HUANG

2020, 6(1):  84-93.  doi:10.11959/j.issn.2096-109x.2020007

Asbtract ( 428 )   HTML ( 34)   PDF (1060KB) ( 274 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Traditional passive forensics of video inter-frame tampering often relies on single feature.Each of these features is usually suitable for certain types of videos,while has low detection accuracy for other videos.To combine the advantages of these features,a video inter-frame tampering detection algorithm that could fuse multi-features was proposed.The algorithm firstly classified the input video into one group based on its space information and time information values.Then it calculated the VQA features that represented the video inter-frame continuity.These features were sorted by the SVM-RFE feature recursive elimination algorithm.Finally,the sorted features were filtered and fused by the sequential forward selection algorithm and Adaboost binary classifier.Experimental results show that the proposed algorithm could achieve higher tampering detection accuracy.

Automatic detection method of software upgrade vulnerability based on network traffic analysis

Jinhui TENG,Yan GUANG,Hui SHU,Bing ZHANG

2020, 6(1):  94-108.  doi:10.11959/j.issn.2096-109x.2020004

Asbtract ( 380 )   HTML ( 45)   PDF (2711KB) ( 402 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

During the software upgrade process,the lack of authentication for upgrade information or packages can lead to remote code execution vulnerabilities based on man-in-the-middle attack.An automatic detection method for upgrading vulnerabilities was proposed.The method described the upgrade mechanism by extracting the network traffic during the upgrade process,then matched it with the vulnerability feature vector to anticipate upgrading vulnerabilities.In a validation environment,the man-in-the-middle attack using the portrait information was carried out to verify the detection results.In addition,an automatic vulnerability analysis and verification system based on this method was designed.184 Windows applications samples was test and 117 upgrade vulnerabilities were detected in these samples,which proved validity of the method.