To address the problem of network security situation assessment in the Industrial Internet,this paper adopts the evidential reasoning(ER)algorithm and belief rule base(BRB)method to establish an assessment model.First...To address the problem of network security situation assessment in the Industrial Internet,this paper adopts the evidential reasoning(ER)algorithm and belief rule base(BRB)method to establish an assessment model.First,this paper analyzes the influencing factors of the Industrial Internet and selects evaluation indicators that contain not only quantitative data but also qualitative knowledge.Second,the evaluation indicators are fused with expert knowledge and the ER algorithm.According to the fusion results,a network security situation assessment model of the Industrial Internet based on the ER and BRB method is established,and the projection covariance matrix adaptive evolution strategy(P-CMA-ES)is used to optimize the model parameters.This method can not only utilize semiquantitative information effectively but also use more uncertain information and prevent the problem of combinatorial explosion.Moreover,it solves the problem of the uncertainty of expert knowledge and overcomes the problem of low modeling accuracy caused by insufficient data.Finally,a network security situation assessment case of the Industrial Internet is analyzed to verify the effectiveness and superiority of the method.The research results showthat this method has strong applicability to the network security situation assessment of complex Industrial Internet systems.It can accurately reflect the actual network security situation of Industrial Internet systems and provide safe and reliable suggestions for network administrators to take timely countermeasures,thereby improving the risk monitoring and emergency response capabilities of the Industrial Internet.展开更多
Particle filter is a common algorithm in video target tracking.But there are still some shortcomings,for example,particle degradation phenomenon.For solving this problem,the general solution is to introduce resampling...Particle filter is a common algorithm in video target tracking.But there are still some shortcomings,for example,particle degradation phenomenon.For solving this problem,the general solution is to introduce resampling step.At present,four kinds of resampling algorithms are widely used:multinomial resampling,residual resampling,stratified resampling and systematic resampling algorithms.In this paper,the performances of these four resampling algorithms were analyzed from realization principle,uniform distribution theory and computational complexity.Finally,through a series of video target tracking experiments,the systematic resampling algorithm had the smallest calculation load,the shortest running time and the maximum number of effective particles.So,it can be concluded that in the field of video target tracking,the systematic resampling algorithm has more advantages than other three algorithms both in the running time and the number of effective particles.展开更多
Limited contact capacity and heterogeneous adoption thresholds have been proven to be two essential characteristics of individuals in natural complex social systems,and their impacts on social contagions exhibit compl...Limited contact capacity and heterogeneous adoption thresholds have been proven to be two essential characteristics of individuals in natural complex social systems,and their impacts on social contagions exhibit complex nature.With this in mind,a heterogeneous contact-limited threshold model is proposed,which adopts one of four threshold distributions,namely Gaussian distribution,log-normal distribution,exponential distribution and power-law distribution.The heterogeneous edge-based compartmental theory is developed for theoretical analysis,and the calculation methods of the final adoption size and outbreak threshold are given theoretically.Many numerical simulations are performed on the Erdös-Renyi and scale-free networks to study the impact of different forms of the threshold distribution on hierarchical spreading´process,the final adoption size,the outbreak threshold and the phase transition in contact-limited propagation networks.We find that the spreading process of social contagions is divided into three distinct stages.Moreover,different threshold distributions cause different spreading processes,especially for some threshold distributions,there is a change from a discontinuous first-order phase transition to a continuous second-order phase transition.Further,we find that changing the standard deviation of different threshold distributions will cause the final adoption size and outbreak threshold to change,and finally tend to be stable with the increase of standard deviation.展开更多
Sybil attacks are one of the most prominent security problems of trust mechanisms in a distributed network with a large number of highly dynamic and heterogeneous devices,which expose serious threat to edge computing ...Sybil attacks are one of the most prominent security problems of trust mechanisms in a distributed network with a large number of highly dynamic and heterogeneous devices,which expose serious threat to edge computing based distributed systems.Graphbased Sybil detection approaches extract social structures from target distributed systems,refine the graph via preprocessing methods and capture Sybil nodes based on the specific properties of the refined graph structure.Graph preprocessing is a critical component in such Sybil detection methods,and intuitively,the processing methods will affect the detection performance.Thoroughly understanding the dependency on the graph-processing methods is very important to develop and deploy Sybil detection approaches.In this paper,we design experiments and conduct systematic analysis on graph-based Sybil detection with respect to different graph preprocessing methods on selected network environments.The experiment results disclose the sensitivity caused by different graph transformations on accuracy and robustness of Sybil detection methods.展开更多
Heap overflow attack is one of the major memory corruption attacks that have become prevalent for decades. To defeat this attack,many protection methods are proposed in recent years. However,most of these existing met...Heap overflow attack is one of the major memory corruption attacks that have become prevalent for decades. To defeat this attack,many protection methods are proposed in recent years. However,most of these existing methods focus on user-level heap overflow detection. Only a few methods are proposed for kernel heap protection. Moreover,all these kernel protection methods need modifying the existing OS kernel so that they may not be adopted in practice. To address this problem,we propose a lightweight virtualization-based solution that can protect the kernel heap buffers allocated for the target kernel modules. The key idea of our approach is to combine the static binary analysis and virtualization technology to trap a memory allocation operation of the target kernel module,and then add one secure canary word to the end of the allocated buffer. After that,a monitor process is launched to check the integrity of the canaries. The evaluations show that our system can detect kernel heap overflow attacks effectively with minimal performance cost.展开更多
Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natur...Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natural language instruction and the observed surrounding visual information. To make the best decision, in every step during the navigation, the agent should pay more attention to understanding the objects, the object attributes, and the object relationships. But most current methods process all received textual and visual information equally. Therefore, this paper integrates more detailed semantic connections between visual and textual information through three pre-training tasks(object prediction, object attributes prediction, and object relationship prediction). The model will learn better fusion representation and alignment between these two types of information to improve the success rate(SR) and generalization. The experiments show that compared with the former baseline models, the SR on the unseen validation set(Val Unseen) increased by 7%, and the SR weighted by path length(SPL) increased by 7%;the SR on the test set(Test) increased 4%, SPL increased by 3%.展开更多
The Product Sensitive Online Dirichlet Allocation model(PSOLDA)proposed in this paper mainly uses the sentiment polarity of topic words in the review text to improve the accuracy of topic evolution.First,we use Latent...The Product Sensitive Online Dirichlet Allocation model(PSOLDA)proposed in this paper mainly uses the sentiment polarity of topic words in the review text to improve the accuracy of topic evolution.First,we use Latent Dirichlet Allocation(LDA)to obtain the distribution of topic words in the current time window.Second,the word2 vec word vector is used as auxiliary information to determine the sentiment polarity and obtain the sentiment polarity distribution of the current topic.Finally,the sentiment polarity changes of the topics in the previous and next time window are mapped to the sentiment factors,and the distribution of topic words in the next time window is controlled through them.The experimental results show that the PSOLDA model decreases the probability distribution by 0.1601,while Online Twitter LDA only increases by 0.0699.The topic evolution method that integrates the sentimental information of topic words proposed in this paper is better than the traditional model.展开更多
基金supported by the Provincial Universities Basic Business Expense Scientific Research Projects of Heilongjiang Province(No.2021-KYYWF-0179)the Science and Technology Project of Henan Province(No.212102310991)+2 种基金the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security(No.AGK2015003)the Key Scientific Research Project of Henan Province(No.21A413001)the Postgraduate Innovation Project of Harbin Normal University(No.HSDSSCX2021-121).
文摘To address the problem of network security situation assessment in the Industrial Internet,this paper adopts the evidential reasoning(ER)algorithm and belief rule base(BRB)method to establish an assessment model.First,this paper analyzes the influencing factors of the Industrial Internet and selects evaluation indicators that contain not only quantitative data but also qualitative knowledge.Second,the evaluation indicators are fused with expert knowledge and the ER algorithm.According to the fusion results,a network security situation assessment model of the Industrial Internet based on the ER and BRB method is established,and the projection covariance matrix adaptive evolution strategy(P-CMA-ES)is used to optimize the model parameters.This method can not only utilize semiquantitative information effectively but also use more uncertain information and prevent the problem of combinatorial explosion.Moreover,it solves the problem of the uncertainty of expert knowledge and overcomes the problem of low modeling accuracy caused by insufficient data.Finally,a network security situation assessment case of the Industrial Internet is analyzed to verify the effectiveness and superiority of the method.The research results showthat this method has strong applicability to the network security situation assessment of complex Industrial Internet systems.It can accurately reflect the actual network security situation of Industrial Internet systems and provide safe and reliable suggestions for network administrators to take timely countermeasures,thereby improving the risk monitoring and emergency response capabilities of the Industrial Internet.
基金National Natural Science Foundations of China(Nos.61272097,61305014,61401257)China Scholarship Council(No.201508310033)+5 种基金Innovation Program of Shanghai Municipal Education Commission,China(No.14ZZ156)Natural Science Foundation of Shanghai,China(No.13ZR1455200)"Chen Guang"Project Supported by Shanghai Municipal Education Commission and Shanghai Education Development Foundation,China(No.13CG60)Funding Scheme for Training Young Teachers in Shanghai Colleges,China(No.ZZGJD13006)The Connotative Construction Projects of Shanghai Local Colleges in the 12th Five-Year,China(Nos.nhky-201442,nhrc-2015-11)The Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security,China(No.AGK2015006)
文摘Particle filter is a common algorithm in video target tracking.But there are still some shortcomings,for example,particle degradation phenomenon.For solving this problem,the general solution is to introduce resampling step.At present,four kinds of resampling algorithms are widely used:multinomial resampling,residual resampling,stratified resampling and systematic resampling algorithms.In this paper,the performances of these four resampling algorithms were analyzed from realization principle,uniform distribution theory and computational complexity.Finally,through a series of video target tracking experiments,the systematic resampling algorithm had the smallest calculation load,the shortest running time and the maximum number of effective particles.So,it can be concluded that in the field of video target tracking,the systematic resampling algorithm has more advantages than other three algorithms both in the running time and the number of effective particles.
基金supported by the National Natural Science Foundation of China(Grant Nos.62072412,61902359,61672467,and 61672468)the Social Development Project of Zhejiang Provincial Public Technology Research(Grant No.2016C33168)+1 种基金Zhejiang Provincial Natural Science Foundation of China(Grant No.LQ19F030010)the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security(Grant No.AGK2018001).
文摘Limited contact capacity and heterogeneous adoption thresholds have been proven to be two essential characteristics of individuals in natural complex social systems,and their impacts on social contagions exhibit complex nature.With this in mind,a heterogeneous contact-limited threshold model is proposed,which adopts one of four threshold distributions,namely Gaussian distribution,log-normal distribution,exponential distribution and power-law distribution.The heterogeneous edge-based compartmental theory is developed for theoretical analysis,and the calculation methods of the final adoption size and outbreak threshold are given theoretically.Many numerical simulations are performed on the Erdös-Renyi and scale-free networks to study the impact of different forms of the threshold distribution on hierarchical spreading´process,the final adoption size,the outbreak threshold and the phase transition in contact-limited propagation networks.We find that the spreading process of social contagions is divided into three distinct stages.Moreover,different threshold distributions cause different spreading processes,especially for some threshold distributions,there is a change from a discontinuous first-order phase transition to a continuous second-order phase transition.Further,we find that changing the standard deviation of different threshold distributions will cause the final adoption size and outbreak threshold to change,and finally tend to be stable with the increase of standard deviation.
基金the National Key R&D Program of China(No.2017YFB0802403)the Beijing Natural Science Foundation(No.4202036)+1 种基金the National Natural Science Foundation of China(No.U1733115,No.61871023)the Opening Project of Shanghai Key Laboratory of Inte grated Administration Technologies for Information Security(No.AGK2019001).
文摘Sybil attacks are one of the most prominent security problems of trust mechanisms in a distributed network with a large number of highly dynamic and heterogeneous devices,which expose serious threat to edge computing based distributed systems.Graphbased Sybil detection approaches extract social structures from target distributed systems,refine the graph via preprocessing methods and capture Sybil nodes based on the specific properties of the refined graph structure.Graph preprocessing is a critical component in such Sybil detection methods,and intuitively,the processing methods will affect the detection performance.Thoroughly understanding the dependency on the graph-processing methods is very important to develop and deploy Sybil detection approaches.In this paper,we design experiments and conduct systematic analysis on graph-based Sybil detection with respect to different graph preprocessing methods on selected network environments.The experiment results disclose the sensitivity caused by different graph transformations on accuracy and robustness of Sybil detection methods.
基金supported in part by National Natural Science Foundation of China (NSFC) under Grant No.61602035the National Key Research and Development Program of China under Grant No.2016YFB0800700+1 种基金the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information SecurityOpen Found of Key Laboratory of IOT Application Technology of Universities in Yunnan Province under Grant No.2015IOT03
文摘Heap overflow attack is one of the major memory corruption attacks that have become prevalent for decades. To defeat this attack,many protection methods are proposed in recent years. However,most of these existing methods focus on user-level heap overflow detection. Only a few methods are proposed for kernel heap protection. Moreover,all these kernel protection methods need modifying the existing OS kernel so that they may not be adopted in practice. To address this problem,we propose a lightweight virtualization-based solution that can protect the kernel heap buffers allocated for the target kernel modules. The key idea of our approach is to combine the static binary analysis and virtualization technology to trap a memory allocation operation of the target kernel module,and then add one secure canary word to the end of the allocated buffer. After that,a monitor process is launched to check the integrity of the canaries. The evaluations show that our system can detect kernel heap overflow attacks effectively with minimal performance cost.
基金Supported by the National Natural Science Foundation of China (62006150)Songjiang District Science and Technology Research Project (19SJKJGG83)Shanghai Young Science and Technology Talents Sailing Program (19YF1418400)。
文摘Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natural language instruction and the observed surrounding visual information. To make the best decision, in every step during the navigation, the agent should pay more attention to understanding the objects, the object attributes, and the object relationships. But most current methods process all received textual and visual information equally. Therefore, this paper integrates more detailed semantic connections between visual and textual information through three pre-training tasks(object prediction, object attributes prediction, and object relationship prediction). The model will learn better fusion representation and alignment between these two types of information to improve the success rate(SR) and generalization. The experiments show that compared with the former baseline models, the SR on the unseen validation set(Val Unseen) increased by 7%, and the SR weighted by path length(SPL) increased by 7%;the SR on the test set(Test) increased 4%, SPL increased by 3%.
基金supported by the National Natural Science Foundation of China(No.61433006)the Key Research Project of Zhejiang Province,China(No.2017C01062)+3 种基金the Open Research Project of the State Key Laboratory of Industrial Control Technology,Zhejiang University,China(No.ICT1800422)the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security,China(No.AGK2018003)the Department of Education of Zhejiang Province,China(No.Y201840611)the Zhejiang Provincial Natural Science Foundation of China(No.LY16F020019)
基金Supported by the Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security(AGK2019004)Songjiang District Science and Technology Research Project(19SJKJGG83)National Natural Science Foundation of China(61802251)。
文摘The Product Sensitive Online Dirichlet Allocation model(PSOLDA)proposed in this paper mainly uses the sentiment polarity of topic words in the review text to improve the accuracy of topic evolution.First,we use Latent Dirichlet Allocation(LDA)to obtain the distribution of topic words in the current time window.Second,the word2 vec word vector is used as auxiliary information to determine the sentiment polarity and obtain the sentiment polarity distribution of the current topic.Finally,the sentiment polarity changes of the topics in the previous and next time window are mapped to the sentiment factors,and the distribution of topic words in the next time window is controlled through them.The experimental results show that the PSOLDA model decreases the probability distribution by 0.1601,while Online Twitter LDA only increases by 0.0699.The topic evolution method that integrates the sentimental information of topic words proposed in this paper is better than the traditional model.
