Network optimization and policy deployment need the underlying state information as a reference basis. However, the timeliness of information collection will seriously affect the effectiveness of optimization results. As a key index, link bandwidth has a guiding significance for network management such as routing, queue scheduling and congestion control. In this paper, we use the theory of degree centrality-based critical node ranking in complex networks to implement fast link bandwidth measurements in software-defined networks. Simulation results on several real topologies of different sizes verify the advantages of our scheme over existing algorithms in terms of measurement time overhead and robustness to different measurement methods.
{"title":"Leveraging Degree Centrality for Fast Bandwidth Measurement in OpenFlow-based SDN","authors":"Binghao Yan, Qinrang Liu, Dong Liang, Haiming Zhao, JianLiang Shen","doi":"10.1109/IEEECONF52377.2022.10013104","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013104","url":null,"abstract":"Network optimization and policy deployment need the underlying state information as a reference basis. However, the timeliness of information collection will seriously affect the effectiveness of optimization results. As a key index, link bandwidth has a guiding significance for network management such as routing, queue scheduling and congestion control. In this paper, we use the theory of degree centrality-based critical node ranking in complex networks to implement fast link bandwidth measurements in software-defined networks. Simulation results on several real topologies of different sizes verify the advantages of our scheme over existing algorithms in terms of measurement time overhead and robustness to different measurement methods.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130791150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of cloud computing technology, more and more scientific researchers choose to deliver scientific workflow tasks to public cloud platforms for execution. This mode effectively reduces scientific research costs while also bringing serious security risks. In response to this problem, this article summarizes the current security issues facing cloud scientific workflows, and analyzes the importance of studying cloud scientific workflow security issues. Then this article analyzes, summarizes and compares the current cloud scientific workflow security methods from three perspectives: system architecture, security model, and security strategy. Finally made a prospect for the future development direction.
{"title":"Overview of Scientific Workflow Security Scheduling in Clouds","authors":"Xuanyu Liu, Guozhen Cheng, Ya-wen Wang, Shuai Zhang","doi":"10.1109/IEEECONF52377.2022.10013096","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013096","url":null,"abstract":"With the development of cloud computing technology, more and more scientific researchers choose to deliver scientific workflow tasks to public cloud platforms for execution. This mode effectively reduces scientific research costs while also bringing serious security risks. In response to this problem, this article summarizes the current security issues facing cloud scientific workflows, and analyzes the importance of studying cloud scientific workflow security issues. Then this article analyzes, summarizes and compares the current cloud scientific workflow security methods from three perspectives: system architecture, security model, and security strategy. Finally made a prospect for the future development direction.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129849692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013094
Ya Liu, Kaizhi Huang, Shaochuan Yang, Jie Yang, Xiaoli Sun
Physical layer secret key generation (SKG) is a promising supplement for high-level encryption, which leverages the channel reciprocity and the natural randomness of wireless channel. However, practical implementations often exhibit static environment. To solve this problem, this paper proposes a novel secret key generation scheme assisted by an intelligent reflecting surface (IRS) which can smartly reconfigure the radio signal propagation to improve the secret key rate of SKG. Specially, we formulate the minimum achievable secret key capacity in the IRS-assisted multiple-input single-output (MISO) system with multiple eavesdroppers. Then, an optimization framework for designing IRS reflecting coefficients based on the secret key capacity lower bound is proposed. Numerical results show that our optimal IRS-assisted SKG scheme can achieve much higher achievable secret key capacity when compared with two benchmark schemes.
{"title":"Secret Key Generation for Intelligent Reflecting Surface Assisted Wireless Communication Networks with Multiple Eavesdroppers","authors":"Ya Liu, Kaizhi Huang, Shaochuan Yang, Jie Yang, Xiaoli Sun","doi":"10.1109/IEEECONF52377.2022.10013094","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013094","url":null,"abstract":"Physical layer secret key generation (SKG) is a promising supplement for high-level encryption, which leverages the channel reciprocity and the natural randomness of wireless channel. However, practical implementations often exhibit static environment. To solve this problem, this paper proposes a novel secret key generation scheme assisted by an intelligent reflecting surface (IRS) which can smartly reconfigure the radio signal propagation to improve the secret key rate of SKG. Specially, we formulate the minimum achievable secret key capacity in the IRS-assisted multiple-input single-output (MISO) system with multiple eavesdroppers. Then, an optimization framework for designing IRS reflecting coefficients based on the secret key capacity lower bound is proposed. Numerical results show that our optimal IRS-assisted SKG scheme can achieve much higher achievable secret key capacity when compared with two benchmark schemes.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130974599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The primary purpose of acquiring network security situation elements is to detect and discover potential security threats from discrete and isolated data. In the complex network environment, the existing network security situation element acquisition technology has the problems of low extraction accuracy and low extraction efficiency. To solve these problems, a method for extracting network security situation elements based on Gradient Boosting Decision Tree (GBDT) is proposed. This method uses the attribute reduction function of rough set to preprocess the original data, which can effectively reduce redundancy. Furthermore, the initial parameters of GBDT are optimized by quantum particle swarm optimization (QPSO) algorithm to improve stability. Finally, the optimized GBDT classifier is used to classify and train with the reduced data set, and the accuracy of the final classifier is continuously improved by reducing the deviation via iterative optimization. Experiments demonstrate that the proposed algorithm achieves significant results and outperforms several state-of-the-art algorithms to the extraction of network security situation elements on the UNSW-NB15 dataset.
{"title":"An Extraction Method of Network Security Situation Elements Based on Gradient Lifting Decision Tree","authors":"Zhaorui Ma, Shicheng Zhang, Yiheng Chang, Q. Zhou, Xinhao Hu, Xia Li","doi":"10.1109/IEEECONF52377.2022.10013351","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013351","url":null,"abstract":"The primary purpose of acquiring network security situation elements is to detect and discover potential security threats from discrete and isolated data. In the complex network environment, the existing network security situation element acquisition technology has the problems of low extraction accuracy and low extraction efficiency. To solve these problems, a method for extracting network security situation elements based on Gradient Boosting Decision Tree (GBDT) is proposed. This method uses the attribute reduction function of rough set to preprocess the original data, which can effectively reduce redundancy. Furthermore, the initial parameters of GBDT are optimized by quantum particle swarm optimization (QPSO) algorithm to improve stability. Finally, the optimized GBDT classifier is used to classify and train with the reduced data set, and the accuracy of the final classifier is continuously improved by reducing the deviation via iterative optimization. Experiments demonstrate that the proposed algorithm achieves significant results and outperforms several state-of-the-art algorithms to the extraction of network security situation elements on the UNSW-NB15 dataset.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122984415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013353
Siyi Hong, Yi He, Jianpeng Zhang, Chao Jiang, Yingjun Deng
In modern industry, the accurate prediction of remaining useful life(RUL) contributes to the equipment safety and economic effectiveness. Aiming at the RUL prediction, this paper proposed a Bayesian temporal convolutional network (BayesianTCN) under the Bayesian deep learning framework. BayesianTCN outputs not only the RUL prediction, but also the associated confidence interval by Monte-Carlo simulation. This quantifies the RUL prediction uncertainty. Experimental results on CMAPSS datasets show that our model has higher fitting degree and lower uncertainty than BayesianLSTM, and performs well whether in simple or complex conditions.
{"title":"Remaining Useful Life Prediction via Bayesian Temporal Convolutional Networks","authors":"Siyi Hong, Yi He, Jianpeng Zhang, Chao Jiang, Yingjun Deng","doi":"10.1109/IEEECONF52377.2022.10013353","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013353","url":null,"abstract":"In modern industry, the accurate prediction of remaining useful life(RUL) contributes to the equipment safety and economic effectiveness. Aiming at the RUL prediction, this paper proposed a Bayesian temporal convolutional network (BayesianTCN) under the Bayesian deep learning framework. BayesianTCN outputs not only the RUL prediction, but also the associated confidence interval by Monte-Carlo simulation. This quantifies the RUL prediction uncertainty. Experimental results on CMAPSS datasets show that our model has higher fitting degree and lower uncertainty than BayesianLSTM, and performs well whether in simple or complex conditions.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129367857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013338
Hui Miao, Q. Zhou, Huawei Song, F. Wan, Xin Yang
The profile study based on the modeling of the dynamic change of user interest is a research method that realizes the dynamic update of interest tags by constructing the time decay function of interest transfer, and then constructs the dynamic model to achieve more accurate personalized recommendation and other functions. This article mainly introduces the construction of user interest model based on forgetting mechanism,by comparing various interest models, it can be found that the dynamic change model of interest based on the forgetting mechanism is more capable of constructing a user profile system with accurate delivery effects.
{"title":"Research on User Profile based on Interest Dynamic Change Modeling","authors":"Hui Miao, Q. Zhou, Huawei Song, F. Wan, Xin Yang","doi":"10.1109/IEEECONF52377.2022.10013338","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013338","url":null,"abstract":"The profile study based on the modeling of the dynamic change of user interest is a research method that realizes the dynamic update of interest tags by constructing the time decay function of interest transfer, and then constructs the dynamic model to achieve more accurate personalized recommendation and other functions. This article mainly introduces the construction of user interest model based on forgetting mechanism,by comparing various interest models, it can be found that the dynamic change model of interest based on the forgetting mechanism is more capable of constructing a user profile system with accurate delivery effects.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126565818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013352
Wei You, Mingyan Xu, Deqiang Zhou
5G core network introduces service based architecture, software defined network, network function virtualization and other new technologies, showing the characteristics of IT and Internet. The new architecture and new technologies not only bring convenience to 5G but also introduce new security threats, especially the unknown security threats caused by unknown vulnerabilities or backdoors. This paper mainly introduces the security threats after the application of software defined network, network function virtualization and other technologies to 5G, summarizes the security solutions proposed by standardization organizations and academia, and puts forward a new idea of building a high-level secure 5G core network based on the endogenous safety and security.
{"title":"Research on security protection technology for 5G cloud network","authors":"Wei You, Mingyan Xu, Deqiang Zhou","doi":"10.1109/IEEECONF52377.2022.10013352","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013352","url":null,"abstract":"5G core network introduces service based architecture, software defined network, network function virtualization and other new technologies, showing the characteristics of IT and Internet. The new architecture and new technologies not only bring convenience to 5G but also introduce new security threats, especially the unknown security threats caused by unknown vulnerabilities or backdoors. This paper mainly introduces the security threats after the application of software defined network, network function virtualization and other technologies to 5G, summarizes the security solutions proposed by standardization organizations and academia, and puts forward a new idea of building a high-level secure 5G core network based on the endogenous safety and security.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131364654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013357
Songhao Bai, Zhen Zhang
As one of the effective methods to enhance traffic safety and improve traffic efficiency, the Internet of vehicles has attracted wide attention from all walks of life. V2X secure communication, as one of the research hotspots of the Internet of vehicles, also has many security and privacy problems. Attackers can use these vulnerabilities to obtain vehicle identity information and location information, and can also attack vehicles through camouflage.Therefore, the identity authentication process in vehicle network communication must be effectively protected. The anonymous identity authentication scheme based on moving target defense proposed in this paper not only ensures the authenticity and integrity of information sources, but also avoids the disclosure of vehicle identity information.
{"title":"Anonymous Identity Authentication scheme for Internet of Vehicles based on moving target Defense","authors":"Songhao Bai, Zhen Zhang","doi":"10.1109/IEEECONF52377.2022.10013357","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013357","url":null,"abstract":"As one of the effective methods to enhance traffic safety and improve traffic efficiency, the Internet of vehicles has attracted wide attention from all walks of life. V2X secure communication, as one of the research hotspots of the Internet of vehicles, also has many security and privacy problems. Attackers can use these vulnerabilities to obtain vehicle identity information and location information, and can also attack vehicles through camouflage.Therefore, the identity authentication process in vehicle network communication must be effectively protected. The anonymous identity authentication scheme based on moving target defense proposed in this paper not only ensures the authenticity and integrity of information sources, but also avoids the disclosure of vehicle identity information.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130116913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013336
Kai Liu, Yu Li, Ouyang Ling
Fault tolerance is gaining more and more attention for the increasing need of reliability in industrial, automotive and aerospace applications. This paper presents a survey of the fault tolerance mechanism to provide reliability against radiation-induced soft errors at the hardware architectural level. Multiple types of error detection and error recovery mechanisms based on lockstep are described in this article, and a discussion of their advantages and disadvantages is given at the end.
{"title":"A survey of fault tolerance hardware architecture","authors":"Kai Liu, Yu Li, Ouyang Ling","doi":"10.1109/IEEECONF52377.2022.10013336","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013336","url":null,"abstract":"Fault tolerance is gaining more and more attention for the increasing need of reliability in industrial, automotive and aerospace applications. This paper presents a survey of the fault tolerance mechanism to provide reliability against radiation-induced soft errors at the hardware architectural level. Multiple types of error detection and error recovery mechanisms based on lockstep are described in this article, and a discussion of their advantages and disadvantages is given at the end.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128255526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013348
Shiyuan Yu, Shuming Guo, Ruiyang Huang, Jianpeng Zhang, Ke Su, Nan Hu
Word-level information is crucial for Chinese named entity recognition. Presently, most works have achieved better performance by extracting word-level information into character-level representations through existing lexicons, but the maintenance of lexical lists is a major challenge. In this paper, we present the NIMSI model, proposing the incorporation of multiple segmentation information to enhance recognition, using a trilogy to align character-level attention with word-level attention to construct features of segmented information in Chinese text. Also, we use a simple but effective method to directly incorporate multi-segmentation information into character-level representations. Finally, as the experiments on the three benchmark datasets show, our model effectively incorporates segmentation information and alleviates the segmentation errors.
{"title":"Named Entity Recognition Incorporating Chinese Segmentation Information","authors":"Shiyuan Yu, Shuming Guo, Ruiyang Huang, Jianpeng Zhang, Ke Su, Nan Hu","doi":"10.1109/IEEECONF52377.2022.10013348","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013348","url":null,"abstract":"Word-level information is crucial for Chinese named entity recognition. Presently, most works have achieved better performance by extracting word-level information into character-level representations through existing lexicons, but the maintenance of lexical lists is a major challenge. In this paper, we present the NIMSI model, proposing the incorporation of multiple segmentation information to enhance recognition, using a trilogy to align character-level attention with word-level attention to construct features of segmented information in Chinese text. Also, we use a simple but effective method to directly incorporate multi-segmentation information into character-level representations. Finally, as the experiments on the three benchmark datasets show, our model effectively incorporates segmentation information and alleviates the segmentation errors.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"57 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133940748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：