Smart city refers to the information system with Intemet of things and cloud computing as the core tec hnology and government management and industrial development as the core content,forming a large scale,heterogeneo...Smart city refers to the information system with Intemet of things and cloud computing as the core tec hnology and government management and industrial development as the core content,forming a large scale,heterogeneous and dynamic distributed Internet of things environment between different Internet of things.There is a wide demand for cooperation between equipment and management institutions in the smart city.Therefore,it is necessary to establish a trust mechanism to promote cooperation,and based on this,prevent data disorder caused by the interaction between honest terminals and malicious temminals.However,most of the existing research on trust mechanism is divorced from the Internet of things environment,and does not consider the characteristics of limited computing and storage capacity and large differences of Internet of hings devices,resuling in the fact that the research on abstract trust trust mechanism cannot be directly applied to the Internet of things;On the other hand,various threats to the Internet of things caused by security vulnerabilities such as collision attacks are not considered.Aiming at the security problems of cross domain trusted authentication of Intelligent City Internet of things terminals,a cross domain trust model(CDTM)based on self-authentication is proposed.Unlike most trust models,this model uses self-certified trust.The cross-domain process of internet of things(IoT)terminal can quickly establish a trust relationship with the current domain by providing its trust certificate stored in the previous domain interaction.At the same time,in order to alleviate the collision attack and improve the accuracy of trust evaluation,the overall trust value is calculated by comprehensively considering the quantity weight,time attenuation weight and similarity weight.Finally,the simulation results show that CDTM has good anti collusion attack ability.The success rate of malicious interaction will not increase significantly.Compared with other models,the resource consumption of our proposed model is significantly reduced.展开更多
With the development of sensor technology and wireless communication technology,edge computing has a wider range of applications.The privacy protection of edge computing is of great significance.In the edge computing ...With the development of sensor technology and wireless communication technology,edge computing has a wider range of applications.The privacy protection of edge computing is of great significance.In the edge computing system,in order to ensure the credibility of the source of terminal data,mobile edge computing(MEC)needs to verify the signature of the terminal node on the data.During the signature process,the computing power of edge devices such as wireless terminals can easily become the bottleneck of system performance.Therefore,it is very necessary to improve efficiency through computational offloading.Therefore,this paper proposes an identitybased edge computing anonymous authentication protocol.The protocol realizes mutual authentication and obtains a shared key by encrypting the mutual information.The encryption algorithm is implemented through a thresholded identity-based proxy ring signature.When a large number of terminals offload computing,MEC can set the priority of offloading tasks according to the user’s identity and permissions,thereby improving offloading efficiency.Security analysis shows that the scheme can guarantee the anonymity and unforgeability of signatures.The probability of a malicious node forging a signature is equivalent to cracking the discrete logarithm puzzle.According to the efficiency analysis,in the case of MEC offloading,the computational complexity is significantly reduced,the computing power of edge devices is liberated,and the signature efficiency is improved.展开更多
Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD)...Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.展开更多
In a cloud manufacturing environment with abundant functionally equivalent cloud services,users naturally desire the highest-quality service(s).Thus,a comprehensive measurement of quality of service(QoS)is needed.Opti...In a cloud manufacturing environment with abundant functionally equivalent cloud services,users naturally desire the highest-quality service(s).Thus,a comprehensive measurement of quality of service(QoS)is needed.Opti-mizing the plethora of cloud services has thus become a top priority.Cloud ser-vice optimization is negatively affected by untrusted QoS data,which are inevitably provided by some users.To resolve these problems,this paper proposes a QoS-aware cloud service optimization model and establishes QoS-information awareness and quantification mechanisms.Untrusted data are assessed by an information correction method.The weights discovered by the variable precision Rough Set,which mined the evaluation indicators from historical data,providing a comprehensive performance ranking of service quality.The manufacturing cloud service optimization algorithm thus provides a quantitative reference for service selection.In experimental simulations,this method recommended the optimal services that met users’needs,and effectively reduced the impact of dis-honest users on the selection results.展开更多
基金This paper was sponsored in part by Beijing Postdoctoral Research Foundation(No.2021-ZZ-077,No.2020-YJ-006)Chongqing Industrial Control System Security Situational Awareness Platform,2019 Industrial Internet Innovation and Development Project-Provincial Industrial Control System Security Situational Awareness Platform,Center for Research and Innovation in Software Engineering,School of Computer and Information Science(Southwest University,Chongqing 400175,China)Chongqing Graduate Education Teaching Reform Research Project(yjg203032).
文摘Smart city refers to the information system with Intemet of things and cloud computing as the core tec hnology and government management and industrial development as the core content,forming a large scale,heterogeneous and dynamic distributed Internet of things environment between different Internet of things.There is a wide demand for cooperation between equipment and management institutions in the smart city.Therefore,it is necessary to establish a trust mechanism to promote cooperation,and based on this,prevent data disorder caused by the interaction between honest terminals and malicious temminals.However,most of the existing research on trust mechanism is divorced from the Internet of things environment,and does not consider the characteristics of limited computing and storage capacity and large differences of Internet of hings devices,resuling in the fact that the research on abstract trust trust mechanism cannot be directly applied to the Internet of things;On the other hand,various threats to the Internet of things caused by security vulnerabilities such as collision attacks are not considered.Aiming at the security problems of cross domain trusted authentication of Intelligent City Internet of things terminals,a cross domain trust model(CDTM)based on self-authentication is proposed.Unlike most trust models,this model uses self-certified trust.The cross-domain process of internet of things(IoT)terminal can quickly establish a trust relationship with the current domain by providing its trust certificate stored in the previous domain interaction.At the same time,in order to alleviate the collision attack and improve the accuracy of trust evaluation,the overall trust value is calculated by comprehensively considering the quantity weight,time attenuation weight and similarity weight.Finally,the simulation results show that CDTM has good anti collusion attack ability.The success rate of malicious interaction will not increase significantly.Compared with other models,the resource consumption of our proposed model is significantly reduced.
基金Beijing Postdoctoral Research Foundation(No.2021-ZZ-077,No.2020-YJ-006)Chongqing Industrial Control System Security Situational Awareness Platform,2019 Industrial Internet Innovation and Development Project-Provincial Industrial Control System Security Situational Awareness Platform,Center for Research and Innovation in Software Engineering,School of Computer and Information Science(Southwest University,Chongqing 400175,China)Chongqing Graduate Education Teaching Reform Research Project(yjg203032).
文摘With the development of sensor technology and wireless communication technology,edge computing has a wider range of applications.The privacy protection of edge computing is of great significance.In the edge computing system,in order to ensure the credibility of the source of terminal data,mobile edge computing(MEC)needs to verify the signature of the terminal node on the data.During the signature process,the computing power of edge devices such as wireless terminals can easily become the bottleneck of system performance.Therefore,it is very necessary to improve efficiency through computational offloading.Therefore,this paper proposes an identitybased edge computing anonymous authentication protocol.The protocol realizes mutual authentication and obtains a shared key by encrypting the mutual information.The encryption algorithm is implemented through a thresholded identity-based proxy ring signature.When a large number of terminals offload computing,MEC can set the priority of offloading tasks according to the user’s identity and permissions,thereby improving offloading efficiency.Security analysis shows that the scheme can guarantee the anonymity and unforgeability of signatures.The probability of a malicious node forging a signature is equivalent to cracking the discrete logarithm puzzle.According to the efficiency analysis,in the case of MEC offloading,the computational complexity is significantly reduced,the computing power of edge devices is liberated,and the signature efficiency is improved.
基金This work was supported by the National Natural Science Foundation of China(No.61906006).
文摘Whole brain functional connectivity(FC)patterns obtained from resting-state functional magnetic resonance imaging(rs-fMRI)have been widely used in the diagnosis of brain disorders such as autism spectrum disorder(ASD).Recently,an increasing number of studies have focused on employing deep learning techniques to analyze FC patterns for brain disease classification.However,the high dimensionality of the FC features and the interpretation of deep learning results are issues that need to be addressed in the FC-based brain disease classification.In this paper,we proposed a multi-scale attention-based deep neural network(MSA-DNN)model to classify FC patterns for the ASD diagnosis.The model was implemented by adding a flexible multi-scale attention(MSA)module to the auto-encoder based backbone DNN,which can extract multi-scale features of the FC patterns and change the level of attention for different FCs by continuous learning.Our model will reinforce the weights of important FC features while suppress the unimportant FCs to ensure the sparsity of the model weights and enhance the model interpretability.We performed systematic experiments on the large multi-sites ASD dataset with both ten-fold and leaveone-site-out cross-validations.Results showed that our model outperformed classical methods in brain disease classification and revealed robust intersite prediction performance.We also localized important FC features and brain regions associated with ASD classification.Overall,our study further promotes the biomarker detection and computer-aided classification for ASD diagnosis,and the proposed MSA module is flexible and easy to implement in other classification networks.
基金supported by the National Natural Science Foundation,China (Grant No:61602413,Jianwei Zheng,https://www.nsfc.gov.cn)the Natural Science Foundation of Zhejiang Province (Grant No:LY15E050007,Wenlong Ma,http://zjnsf.kjt.zj.gov.cn/portal/index.html).
文摘In a cloud manufacturing environment with abundant functionally equivalent cloud services,users naturally desire the highest-quality service(s).Thus,a comprehensive measurement of quality of service(QoS)is needed.Opti-mizing the plethora of cloud services has thus become a top priority.Cloud ser-vice optimization is negatively affected by untrusted QoS data,which are inevitably provided by some users.To resolve these problems,this paper proposes a QoS-aware cloud service optimization model and establishes QoS-information awareness and quantification mechanisms.Untrusted data are assessed by an information correction method.The weights discovered by the variable precision Rough Set,which mined the evaluation indicators from historical data,providing a comprehensive performance ranking of service quality.The manufacturing cloud service optimization algorithm thus provides a quantitative reference for service selection.In experimental simulations,this method recommended the optimal services that met users’needs,and effectively reduced the impact of dis-honest users on the selection results.
