����Ŀ¼

15 June 2018, Volume 4 Issue 6

Previous Issue    Next Issue

Comprehensive Review

Research progress and trend of text summarization

Tuosiyu MING, Hongchang CHEN

2018, 4(6):  1-10.  doi:10.11959/j.issn.2096-109x.2018048

Asbtract ( 5701 )   HTML ( 93)   PDF (568KB) ( 10173 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

With the explosive growth of information on the Internet,how to extract useful information from massive information has become a key technical issue.The text summarization technology can compress and extract refined and concise document information from big data,effectively reducing the user information overload problem,and it has become a research hotspot.The domestic and foreign text summarization methods and their concrete realization in recent years were analyzed,the advantages and disadvantages between traditional methods and deep learning summary methods were compared,and a reasonable outlook for future research directions was made.

Papers

Risk assessment method for network attack surface based on Bayesian attack graph

Yuyang ZHOU, Guang CHENG, Chunsheng GUO

2018, 4(6):  11-22.  doi:10.11959/j.issn.2096-109x.2018053

Asbtract ( 1830 )   HTML ( 35)   PDF (886KB) ( 2844 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the lack of objective risk assessment for the network attack surface on moving target defense,in order to realize the security risk assessment for the network system,and calculate the potential attack paths,a risk assessment method for network attack surface based on Bayesian attack graph was proposed.The network system resources,vulnerability and dependencies between them were used to establish Bayesian attack graph.Considering dependencies between nodes,the correlation between the resource and the influence of attacks on the attack path,the probability of each state that attackers can reach and the maximum probability attack path can be inferred.The experimental results prove the feasibility and effectiveness of the proposed network attack surface risk assessment method,which can provide a good support for the selection of dynamic defensive measures of attack surface.

Service function chain deployment scheme based on heterogeneous backup and remapping

Jichao XIE,Peng YI,Zhen ZHANG,Chuanhao ZHANG,Yunjie GU

2018, 4(6):  23-35.  doi:10.11959/j.issn.2096-109x.2018051

Asbtract ( 1497 )   HTML ( 9)   PDF (1292KB) ( 1227 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Network function virtualization technology improves the flexibility of service function chains' deployment.However,the virtual network functions are under the pressure of uncertain failures and malicious attacks.The existing redundant backup methods can solve the problem of VNF failures to some extent,it does not consider the defects of node homogeneity in the face of malicious attacks.A deployment method considering the heterogeneity of nodes was proposed,guaranteeing the heterogeneity of nodes when perform redundant backup and remapping.Simulation experiments demonstrate that the proposed method significantly increases attacker's attack time cost under the cost of the request acceptance rate decreases by 3.8% and the bandwidth consumption increase by 9.2% comparing to the homogeneity backup method.

Living body recognition method based on facial feature point motion

Yulong WANG,Kaiyuan LIU

2018, 4(6):  36-44.  doi:10.11959/j.issn.2096-109x.2018044

Asbtract ( 1382 )   HTML ( 10)   PDF (2751KB) ( 1759 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

A kind of living body recognition method was proposed,which was applied in mobile terminal and based on the deep learning.A facial movements LSTM network was trained using data sets.When users input a random sequence of video,user’s facial feature point data can be gained and whether the video forgery attacks happened will be determined by input user’s facial feature point data into circulation neural network.The test data shows that the proposed method can be protected effectively from photograph attack and video replay attack.

Negative feedback scheduling algorithm based on historical information in SDN

Yingying LYU,Yunfei GUO,Zhenpeng WANG,Guozhen CHENG,Yawen WANG

2018, 4(6):  45-51.  doi:10.11959/j.issn.2096-109x.2018047

Asbtract ( 1581 )   HTML ( 8)   PDF (742KB) ( 1123 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In the current SDN architecture,the controllers suffer from lots of potential attacks.For example,malicious flow rule attacks may introduce fake flow rules to confuse the host.A negative feedback scheduling algorithm based on historical information was proposed,in which hypothesis testing was used to judge the behavior of the attacker and the result will be used as a basis for scheduling.Simulation results and analysis show that,compared with the traditional scheduling methods,the proposed algorithm can increase the attacker’s time cost to a certain extent,so as to effectively defend the attacker’s probe attack.In addition,the more types of controllers,the more difficult it is to break the system.

Rapid IO routing strategy based on improved glowworm swarm optimization algorithm

Congyue YIN,Xingming ZHANG,Quan REN,Shuai WEI

2018, 4(6):  52-61.  doi:10.11959/j.issn.2096-109x.2018054

Asbtract ( 989 )   HTML ( 9)   PDF (634KB) ( 1189 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem of Qo S routing in Rapid IO network,a Rapid IO routing strategy based on improved glowworm swarm optimization algorithm was proposed.Firstly,gaussian mutation and storage mechanism were used to optimize the traditional firefly algorithm.Gaussian mutation can effectively control the scattering degree of the solution in the search space of the algorithm,so that the algorithm avoids falling into a local optimum.The storage mechanism is conducive to evaluating and storing the historical state of each glowworm,preventing information loss.Then combine the improved glowworm swarm optimization algorithm with the actual Rapid IO network Qo S problem and select the final best routing strategy.The experimental results show that in the simulated Rapid IO test network,the improved glowworm swarm optimization algorithm has a delay of 42 ms,delayed jitter of 8 ms,a minimum cost of 64 ms,and a total of 8 iterations,which is more stable than other algorithm curves.It can find the optimal solution more quickly and show the best performance,effectively solving the Qo S routing problem of Rapid IO network.

Research and realization on USBKEY based network storage user data protection

Xiao YU,Li TIAN,Zhe LIU,Jie WANG

2018, 4(6):  62-69.  doi:10.11959/j.issn.2096-109x.2018018

Asbtract ( 946 )   HTML ( 2)   PDF (810KB) ( 1109 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

Network storage services such as network hard disk and cloud storage are widely used.However,due to the relative flexibility of network hard disk and cloud storage,it has to face many security risks.Based on the data encryption protection mechanism of USBKEY,data encryption and storage service,the key is stored in USBKEY,will eventually “service level provide security” elaboration to the "real master security" to achieve the purpose of user control of data security.

Control method to prevent malicious UAV intrusion into electricity inspection area

Peng WANG,Xiaolong HAO,Yaokang ZHU,Guang YANG,Yang CUI,Qiwei PENG,Daojing HE

2018, 4(6):  70-76.  doi:10.11959/j.issn.2096-109x.2018052

Asbtract ( 1947 )   HTML ( 16)   PDF (1135KB) ( 1529 )   Knowledge map   

Figures and Tables | References | Related Articles | Metrics

In recent years,the exploitation and deployment of UAV (unmanned aerial vehicle) has grown rapidly.The number of UAV is increasing and it is becoming more and more important in many areas.For example,the power inspection method has be upgraded from the original manual inspection to unmanned intelligent inspection.However,malicious UAV intrude on the power patrol work area and also bring about safety problems to the power plant's production.Because the electronic fence technology (geo-fencing) lacks the real time and flexibility when it controls the UAV,a novel control method to prevent malicious UAV from invading the power inspection area is proposed.The experimental results demonstrate the effectivity of our proposed method.