Pub Date : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345155
Qingqing Zhang, Hongbo Tang, Wei You, Yingle Li
The characteristics of resource sharing and centralized deployment of network function virtualization (NFV) make the physical boundary under the traditional closed management mode disappear, bringing many new security threats to the network. To improve the security of the NFV network, this paper proposes a network function virtualization security architecture based on mimic defense. At the same time, to ensure the differences between heterogeneous entities, a genetic algorithm-based heterogeneous entities pool construction method is proposed. Simulation results show that this method can effectively guarantee the difference between heterogeneous entities and increase the difficulty of attackers.
{"title":"A Method for Constructing Heterogeneous Entities Pool in NFV Security Architecture Based on Mimic Defense","authors":"Qingqing Zhang, Hongbo Tang, Wei You, Yingle Li","doi":"10.1109/ICCC51575.2020.9345155","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345155","url":null,"abstract":"The characteristics of resource sharing and centralized deployment of network function virtualization (NFV) make the physical boundary under the traditional closed management mode disappear, bringing many new security threats to the network. To improve the security of the NFV network, this paper proposes a network function virtualization security architecture based on mimic defense. At the same time, to ensure the differences between heterogeneous entities, a genetic algorithm-based heterogeneous entities pool construction method is proposed. Simulation results show that this method can effectively guarantee the difference between heterogeneous entities and increase the difficulty of attackers.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"355 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123337057","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345161
Xiangdong Lin, W. Zou, Nan Hu, Jiajun Wang
Due to its storage and computation efficiency, hashing has attracted extensive research on large-scale image retrieval tasks in recent years. This work focuses on Hamming space retrieval which enables the most efficient constant-time search by hash table lookups. In this paper, a novel deep supervised hashing method is proposed to generate highly concentrated hash codes based on a redesigned cross-entropy loss function. We also employ a regularizer term to mitigate the discrepancy between the Euclidean distance and the Hamming distance. Extensive experimental results demonstrate the superior performance of our method compared with existing hashing methods on two large-scale image datasets.
{"title":"An Improved Deep Supervised Hashing Method for Hamming Space Retrieval","authors":"Xiangdong Lin, W. Zou, Nan Hu, Jiajun Wang","doi":"10.1109/ICCC51575.2020.9345161","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345161","url":null,"abstract":"Due to its storage and computation efficiency, hashing has attracted extensive research on large-scale image retrieval tasks in recent years. This work focuses on Hamming space retrieval which enables the most efficient constant-time search by hash table lookups. In this paper, a novel deep supervised hashing method is proposed to generate highly concentrated hash codes based on a redesigned cross-entropy loss function. We also employ a regularizer term to mitigate the discrepancy between the Euclidean distance and the Hamming distance. Extensive experimental results demonstrate the superior performance of our method compared with existing hashing methods on two large-scale image datasets.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126538655","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345107
Tianhan Tan, Daolin Chen, Yisong Xue, Jie Zhuang
Array calibration is the guarantee of various array signal processing algorithms. The conventional calibration methods need a large amount of sampling points and calculations. In this paper, we propose an efficient method based on the manifold separation technique (MST) and compressive sensing (CS) to simplify the calibration process. We use the MST to convert the manifold matrix into the product of the sampling matrix and the 2D discrete Fourier transform base. Then by using the CS, we can reduce the required numbe of the measurement points. The simulation results demonstrate that the proposed method achieves the purpose of calibration with less random measurement data.
{"title":"Compressive-Sensing-Based Antenna Array Calibration With Manifold Separation Technique","authors":"Tianhan Tan, Daolin Chen, Yisong Xue, Jie Zhuang","doi":"10.1109/ICCC51575.2020.9345107","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345107","url":null,"abstract":"Array calibration is the guarantee of various array signal processing algorithms. The conventional calibration methods need a large amount of sampling points and calculations. In this paper, we propose an efficient method based on the manifold separation technique (MST) and compressive sensing (CS) to simplify the calibration process. We use the MST to convert the manifold matrix into the product of the sampling matrix and the 2D discrete Fourier transform base. Then by using the CS, we can reduce the required numbe of the measurement points. The simulation results demonstrate that the proposed method achieves the purpose of calibration with less random measurement data.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121593234","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345089
Jinwei Xu, Xu Liu, Xiaorong Zhu
With the rapid development of Internet, continuous emergence of various innovative applications makes current mobile network face pressure of lower latency and computing capability. Mobile edge computing (MEC) has been proposed to be a promising solution to reduce the delay of interaction between applications and compensate the deficiencies of traditional cloud computing. In this paper, we propose a computing offloading and resource allocation algorithm to deal with problems in mobile edge networks (MEN), including offloading decision, transmission power and computation resources allocation. With the goal of minimizing the total cost of the system, an algorithm combining Deep Reinforcement Learning (DRL) and Genetic Algorithm (GA) is used to obtain an approximate optimal solution for the system. Simulation results prove the effectiveness of the algorithm.
{"title":"Deep Reinforcement Learning Based Computing Offloading and Resource Allocation Algorithm for Mobile Edge Networks","authors":"Jinwei Xu, Xu Liu, Xiaorong Zhu","doi":"10.1109/ICCC51575.2020.9345089","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345089","url":null,"abstract":"With the rapid development of Internet, continuous emergence of various innovative applications makes current mobile network face pressure of lower latency and computing capability. Mobile edge computing (MEC) has been proposed to be a promising solution to reduce the delay of interaction between applications and compensate the deficiencies of traditional cloud computing. In this paper, we propose a computing offloading and resource allocation algorithm to deal with problems in mobile edge networks (MEN), including offloading decision, transmission power and computation resources allocation. With the goal of minimizing the total cost of the system, an algorithm combining Deep Reinforcement Learning (DRL) and Genetic Algorithm (GA) is used to obtain an approximate optimal solution for the system. Simulation results prove the effectiveness of the algorithm.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121598748","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345100
Yue Li, Yue Ma, Zhenyu Yin, Ai Gu, Fulong Xu
With the development of intelligent manufacturing, the traditional industrial communication systems based on field bus and industrial Ethernet can hardly meet its common requirements for complexity and scalability in foreseeable future. In contrast, industrial wireless network is not mature yet, and there are still plenty of problems in velocity, stability, security and other aspects. In this paper, a communication model to enhance the comprehensive performance of industrial wireless networks is proposed based on existing scheduling methods of Time-sensitive networks. The model is composed of 3 parts, each of which specifically solves one of the above problems. This research provides research ideas for building a safer and faster wireless communication system for industrial applications.
{"title":"A Communication Model to Enhance Industrial Wireless Networks based on Time-Sensitive Networks","authors":"Yue Li, Yue Ma, Zhenyu Yin, Ai Gu, Fulong Xu","doi":"10.1109/ICCC51575.2020.9345100","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345100","url":null,"abstract":"With the development of intelligent manufacturing, the traditional industrial communication systems based on field bus and industrial Ethernet can hardly meet its common requirements for complexity and scalability in foreseeable future. In contrast, industrial wireless network is not mature yet, and there are still plenty of problems in velocity, stability, security and other aspects. In this paper, a communication model to enhance the comprehensive performance of industrial wireless networks is proposed based on existing scheduling methods of Time-sensitive networks. The model is composed of 3 parts, each of which specifically solves one of the above problems. This research provides research ideas for building a safer and faster wireless communication system for industrial applications.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122330193","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345057
Yao Yuanyuan, Chen Meng
The original Modbus protocol will inevitably cause high bit error rate when there are link problems in the network. Therefore, many experts have proposed to change the frame length according to the BER (bit error rate) to improve the link utilization. However, the link stability of this algorithm is very poor, which leads to the reduction of transmission efficiency. In order to solve the instability problem caused by the traditional adaptive frame length algorithm, an improved adaptive frame length adjustment algorithm is proposed in this paper. According to the average frame error rate in the time period, the method of “fast decrease, slow increase” is used to adjust the data frame length at different levels of FER (frame error rate). This algorithm not only improves the transmission rate, but also improves the stability of the link. Finally, this paper takes the servo drive data acquisition system as the carrier, and verifies the effectiveness of the algorithm through experiments.
{"title":"An Improved Algorithm for Adaptive Communication Frame Length Based on Modbus Protocol","authors":"Yao Yuanyuan, Chen Meng","doi":"10.1109/ICCC51575.2020.9345057","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345057","url":null,"abstract":"The original Modbus protocol will inevitably cause high bit error rate when there are link problems in the network. Therefore, many experts have proposed to change the frame length according to the BER (bit error rate) to improve the link utilization. However, the link stability of this algorithm is very poor, which leads to the reduction of transmission efficiency. In order to solve the instability problem caused by the traditional adaptive frame length algorithm, an improved adaptive frame length adjustment algorithm is proposed in this paper. According to the average frame error rate in the time period, the method of “fast decrease, slow increase” is used to adjust the data frame length at different levels of FER (frame error rate). This algorithm not only improves the transmission rate, but also improves the stability of the link. Finally, this paper takes the servo drive data acquisition system as the carrier, and verifies the effectiveness of the algorithm through experiments.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"52 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114117944","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345217
Ye Peng, Guobin Fu, Yingguang Luo, Qi Yu, Bin Li, Jia Hu
Deep learning plays an increasingly important role in various fields due to its superior performance, and it also achieves advanced recognition performance in the field of image classification. However, the vulnerability of deep learning in the adversarial environment cannot be ignored, and the prediction result of the model is likely to be affected by the small perturbations added to the samples by the adversary. In this paper, we propose a two-layer dynamic defense method based on defensive techniques pool and retrained branch model pool. First, we randomly select defense methods from the defense pool to process the input. The perturbation ability of the adversarial samples preprocessed by different defense methods changed, which would produce different classification results. In addition, we conduct adversarial training based on the original model and dynamically generate multiple branch models. The classification results of these branch models for the same adversarial sample is inconsistent. We can detect the adversarial samples by using the inconsistencies in the output results of the two layers. The experimental results show that the two-layer dynamic defense method we designed achieves a good defense effect.
{"title":"A Two-Layer Moving Target Defense for Image Classification in Adversarial Environment","authors":"Ye Peng, Guobin Fu, Yingguang Luo, Qi Yu, Bin Li, Jia Hu","doi":"10.1109/ICCC51575.2020.9345217","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345217","url":null,"abstract":"Deep learning plays an increasingly important role in various fields due to its superior performance, and it also achieves advanced recognition performance in the field of image classification. However, the vulnerability of deep learning in the adversarial environment cannot be ignored, and the prediction result of the model is likely to be affected by the small perturbations added to the samples by the adversary. In this paper, we propose a two-layer dynamic defense method based on defensive techniques pool and retrained branch model pool. First, we randomly select defense methods from the defense pool to process the input. The perturbation ability of the adversarial samples preprocessed by different defense methods changed, which would produce different classification results. In addition, we conduct adversarial training based on the original model and dynamically generate multiple branch models. The classification results of these branch models for the same adversarial sample is inconsistent. We can detect the adversarial samples by using the inconsistencies in the output results of the two layers. The experimental results show that the two-layer dynamic defense method we designed achieves a good defense effect.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114207361","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344881
J. Yao, Meijuan Chen
Network function virtualization (NFV) technology is widely used in network slicing in 5G networks and traffic processing in wide area network. However, with the increasing of service requests during the life cycle of a virtual network function (VNF), how to flexibly deploy the VNF becomes a key problem to make maximum use of the limited capacity of the physical network resources, and meanwhile satisfy the requirements of quality of service (QoS) in NFV scenario. In this paper, aiming to solve whether and how to scale VNF on demand, we formulated this problem as a non-convex linear mathematical optimization model where the optimization goal is to minimize the delay and energy consumption of the service function chain (SFC). Specifically, we propose a VNF flexible deployment scheme based on Reinforcement Learning (RL). Moreover, we train the agent by interacting with the physical network environment and take action according to the state of physical node to find the optimal physical resource allocation strategy of the VNF scaling. In addition, the state space, action space and the reward function are defined as available resource, migration or scaling decision and the reciprocal of total cost respectively. Extensive simulation results demonstrate that the proposed algorithm outperforms the comparison algorithm in terms of reducing the delay and increasing the ratio of successful scaling request.
{"title":"A Flexible Deployment Scheme for Virtual Network Function Based on Reinforcement Learning","authors":"J. Yao, Meijuan Chen","doi":"10.1109/ICCC51575.2020.9344881","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344881","url":null,"abstract":"Network function virtualization (NFV) technology is widely used in network slicing in 5G networks and traffic processing in wide area network. However, with the increasing of service requests during the life cycle of a virtual network function (VNF), how to flexibly deploy the VNF becomes a key problem to make maximum use of the limited capacity of the physical network resources, and meanwhile satisfy the requirements of quality of service (QoS) in NFV scenario. In this paper, aiming to solve whether and how to scale VNF on demand, we formulated this problem as a non-convex linear mathematical optimization model where the optimization goal is to minimize the delay and energy consumption of the service function chain (SFC). Specifically, we propose a VNF flexible deployment scheme based on Reinforcement Learning (RL). Moreover, we train the agent by interacting with the physical network environment and take action according to the state of physical node to find the optimal physical resource allocation strategy of the VNF scaling. In addition, the state space, action space and the reward function are defined as available resource, migration or scaling decision and the reciprocal of total cost respectively. Extensive simulation results demonstrate that the proposed algorithm outperforms the comparison algorithm in terms of reducing the delay and increasing the ratio of successful scaling request.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121145063","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9345035
Haobo Zhao, Liquan Chen
As a current disruptive and transformative technology, artificial intelligence is constantly infiltrating all aspects of production and life. However, with the in-depth development and application of artificial intelligence, the security challenges it faces have become more and more prominent. In the real world, attacks against intelligent systems such as the Internet of Things, smart homes, and driverless cars are constantly appearing, and incidents of artificial intelligence being used in cyber-attacks and cybercrimes frequently occur. This article aims to discuss artificial intelligence security issues and propose some countermeasures.
{"title":"Artificial Intelligence Security Issues and Responses","authors":"Haobo Zhao, Liquan Chen","doi":"10.1109/ICCC51575.2020.9345035","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9345035","url":null,"abstract":"As a current disruptive and transformative technology, artificial intelligence is constantly infiltrating all aspects of production and life. However, with the in-depth development and application of artificial intelligence, the security challenges it faces have become more and more prominent. In the real world, attacks against intelligent systems such as the Internet of Things, smart homes, and driverless cars are constantly appearing, and incidents of artificial intelligence being used in cyber-attacks and cybercrimes frequently occur. This article aims to discuss artificial intelligence security issues and propose some countermeasures.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116666620","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 : 2020-12-11DOI: 10.1109/ICCC51575.2020.9344930
Xia Liu, Nan Li
With increasing logistics demand and congested surface traffic, underground logistics transportation system has gradually become a forward-looking research and trend. Based on regional center location and logistics demand of logistics parks and regions in an area, this paper builds an underground two-layer logistics system model. Considering constraints such as daily freight volume and service radius of each logistics node, the daily total cost of underground logistics system is minimized. Logistics nodes are selected by K-means and branch and bound method, and network routes are optimized by shortest path method and genetic algorithm. Based on the example data, the node composition, node location and connection route between nodes of the underground logistics network are given.
{"title":"Node Location and Route Optimization of a Two-layer Underground Logistics Network","authors":"Xia Liu, Nan Li","doi":"10.1109/ICCC51575.2020.9344930","DOIUrl":"https://doi.org/10.1109/ICCC51575.2020.9344930","url":null,"abstract":"With increasing logistics demand and congested surface traffic, underground logistics transportation system has gradually become a forward-looking research and trend. Based on regional center location and logistics demand of logistics parks and regions in an area, this paper builds an underground two-layer logistics system model. Considering constraints such as daily freight volume and service radius of each logistics node, the daily total cost of underground logistics system is minimized. Logistics nodes are selected by K-means and branch and bound method, and network routes are optimized by shortest path method and genetic algorithm. Based on the example data, the node composition, node location and connection route between nodes of the underground logistics network are given.","PeriodicalId":386048,"journal":{"name":"2020 IEEE 6th International Conference on Computer and Communications (ICCC)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124936640","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：