Pub Date : 2021-10-01DOI: 10.1109/NaNA53684.2021.00080
Yan Jiao, P. Ho
In this paper, we design a binocular stereo vision system based on an adjustable narrow-baseline stereo camera for extracting depth information from a rectified stereo pair. The camera calibration and rectification are performed to get a rectified stereo pair serving as the input to the stereo matching algorithm. This algorithm searches the corresponding points between the left and right images and produces a disparity map that is used to obtain the depths via the triangulation principle. We focus on the first stage of the algorithm and propose a CNN-based approach to calculating the matching cost. Fast and slow networks are presented and trained on standard stereo datasets. The output of either network is regarded as the initial matching cost, followed by a series of post-processing methods for generating qualified disparity maps. The contrast tests have demonstrated that the CNN-based methods outperform census transformation on the mentioned datasets. Finally, we advance two error criteria to acquire the range of system working distance under diverse baseline lengths.
{"title":"Design of Binocular Stereo Vision System Via CNN-based Stereo Matching Algorithm","authors":"Yan Jiao, P. Ho","doi":"10.1109/NaNA53684.2021.00080","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00080","url":null,"abstract":"In this paper, we design a binocular stereo vision system based on an adjustable narrow-baseline stereo camera for extracting depth information from a rectified stereo pair. The camera calibration and rectification are performed to get a rectified stereo pair serving as the input to the stereo matching algorithm. This algorithm searches the corresponding points between the left and right images and produces a disparity map that is used to obtain the depths via the triangulation principle. We focus on the first stage of the algorithm and propose a CNN-based approach to calculating the matching cost. Fast and slow networks are presented and trained on standard stereo datasets. The output of either network is regarded as the initial matching cost, followed by a series of post-processing methods for generating qualified disparity maps. The contrast tests have demonstrated that the CNN-based methods outperform census transformation on the mentioned datasets. Finally, we advance two error criteria to acquire the range of system working distance under diverse baseline lengths.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124833476","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 : 2021-10-01DOI: 10.1109/NaNA53684.2021.00019
Hengbing Zhu, Huihui Wu, Xiaohong Jiang
Covert communication can be traced back to secret information transmission technology. It aims to ensure that the transmitters and receivers establish reliable communication with a low probability detection by the warden in wireless communications. The scenario of this paper assumes a covert multiple-input-multiple-output (MIMO) communication in a two-hop relay system, in which a transmitter with multi-antenna sends covert messages to a multi-antenna receiver via a single-antenna half-duplex relay against the detection of a single-antenna warden. We first propose an antenna selection scheme to ensure the covertness of communications, where the transmitter and receiver use an optimally selected subset of antennas to transmit or receive the covert messages and the remaining antennas to generate artificial noise (AN). To depict the performance of covert transmission of the system, we analyze the average detection error probability and derive a closed-form expression. We further conduct theoretical covert throughput with a covertness constraint, and analysis to maximize it in the worst case of the system. Finally, the simulation results illustrate the impact of AN, the number of antennas as well as the transmission rate on the performance of this two-hop covert MIMO communication system.
{"title":"Covert MIMO Communication in Two-hop Relay Systems","authors":"Hengbing Zhu, Huihui Wu, Xiaohong Jiang","doi":"10.1109/NaNA53684.2021.00019","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00019","url":null,"abstract":"Covert communication can be traced back to secret information transmission technology. It aims to ensure that the transmitters and receivers establish reliable communication with a low probability detection by the warden in wireless communications. The scenario of this paper assumes a covert multiple-input-multiple-output (MIMO) communication in a two-hop relay system, in which a transmitter with multi-antenna sends covert messages to a multi-antenna receiver via a single-antenna half-duplex relay against the detection of a single-antenna warden. We first propose an antenna selection scheme to ensure the covertness of communications, where the transmitter and receiver use an optimally selected subset of antennas to transmit or receive the covert messages and the remaining antennas to generate artificial noise (AN). To depict the performance of covert transmission of the system, we analyze the average detection error probability and derive a closed-form expression. We further conduct theoretical covert throughput with a covertness constraint, and analysis to maximize it in the worst case of the system. Finally, the simulation results illustrate the impact of AN, the number of antennas as well as the transmission rate on the performance of this two-hop covert MIMO communication system.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125081098","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}
Wireless cooperative relay networks are widely used in various fields. Wireless channels are vulnerable to eavesdroppers because of the broadcast characteristics of wireless channels, the security problem of wireless cooperative relay networks needs to be solved urgently, and the trust level of relays is rarely considered in existing work. Therefore, the paper considers a wireless cooperative relay network with a passive eavesdropping node and untrusted relays and designs a trusted buffer-aided relay selection (TBARS) scheme based on the fact that the channel state information (CSI) of eavesdropping channel is hard to obtain. The paper uses the secrecy outage probability (SOP) to measure the security performance, derives the expression of the SOP based on Markov Process, and verify the feasibility of the TBARS scheme by simulations and analyzes the impact of various factors on the SOP of the TBARS scheme. Finally, the paper compares the TBARS scheme with max-link scheme in terms of the SOP, and the simulations demonstrate that the proposed scheme outperforms the other schemes.
{"title":"Buffer-Aided Relay Selection for Wireless Cooperative Relay Networks with Untrusted Relays","authors":"Cheng Zhang, Xuening Liao, Zhenqiang Wu, Guoyong Qiu","doi":"10.1109/NaNA53684.2021.00020","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00020","url":null,"abstract":"Wireless cooperative relay networks are widely used in various fields. Wireless channels are vulnerable to eavesdroppers because of the broadcast characteristics of wireless channels, the security problem of wireless cooperative relay networks needs to be solved urgently, and the trust level of relays is rarely considered in existing work. Therefore, the paper considers a wireless cooperative relay network with a passive eavesdropping node and untrusted relays and designs a trusted buffer-aided relay selection (TBARS) scheme based on the fact that the channel state information (CSI) of eavesdropping channel is hard to obtain. The paper uses the secrecy outage probability (SOP) to measure the security performance, derives the expression of the SOP based on Markov Process, and verify the feasibility of the TBARS scheme by simulations and analyzes the impact of various factors on the SOP of the TBARS scheme. Finally, the paper compares the TBARS scheme with max-link scheme in terms of the SOP, and the simulations demonstrate that the proposed scheme outperforms the other schemes.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116392921","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 : 2021-10-01DOI: 10.1109/NaNA53684.2021.00043
Yue Zhao, Yarang Yang, Yiru Niu, Dongyu Yang, Bo Tian, Yao Hao, Kaijun Wu
The paper proposed a wireless access authentication mechanism for unmanned systems, which can effectively solve the problem of secure access authentication under the dynamic change of network topology. The authentication process of cooperative authentication and the realization of secure access were designed to meet the application requirements of random access and anti-attack capabilities. The simulation results showed that the cooperative authentication mechanism not only ensures the security of the unmanned system, but also reduces the transmission overhead and the number of interactive authentications. The network access time is less than 30 milliseconds, and the success ratio of network access is close to 100%.
{"title":"The Cooperative Authentication Mechanism and Performance Evaluation for Unmanned Systems","authors":"Yue Zhao, Yarang Yang, Yiru Niu, Dongyu Yang, Bo Tian, Yao Hao, Kaijun Wu","doi":"10.1109/NaNA53684.2021.00043","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00043","url":null,"abstract":"The paper proposed a wireless access authentication mechanism for unmanned systems, which can effectively solve the problem of secure access authentication under the dynamic change of network topology. The authentication process of cooperative authentication and the realization of secure access were designed to meet the application requirements of random access and anti-attack capabilities. The simulation results showed that the cooperative authentication mechanism not only ensures the security of the unmanned system, but also reduces the transmission overhead and the number of interactive authentications. The network access time is less than 30 milliseconds, and the success ratio of network access is close to 100%.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132145039","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}
Graph convolutional network (GCN) and dynamic evolutionary model are the mainstream collaborative filtering technologies in recent years. Nevertheless, the initial feature vectors selection problem of the existing recommendation algorithms based on dynamic evolutionary models leads to unstable recommendation accuracy. In addition, the collaborative filtering method of GCN does not take into account the dynamic evolution law of graph networks. Based on this, this research adopts GCN to train the initial embedding of the dynamic evolution model to perform collaborative filtering recommendation. First of all, a heterogeneous graph network is constructed by applying explicit feedback information (rating scores) of users. Secondly, the embedding of users and items are propagated through the dynamic evolution model. Then, the final embedding is obtained by weighting the embedding of each layer, and the scores are predicted. Finally, according to the Adam optimizer, the initial embedding of the dynamic evolution model is trained in the form of mini-batch to minimize the loss function. Experimental results show that the proposed algorithm is superior to several compared excellent algorithms in recommendation performance.
{"title":"Dyn-GCN: Graph Embedding via Dynamic Evolution and Graph Convolutional Network for Personal Recommendation","authors":"Zhihui Wang, Jianrui Chen, Peijie Wang, Tingting Zhu","doi":"10.1109/NaNA53684.2021.00077","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00077","url":null,"abstract":"Graph convolutional network (GCN) and dynamic evolutionary model are the mainstream collaborative filtering technologies in recent years. Nevertheless, the initial feature vectors selection problem of the existing recommendation algorithms based on dynamic evolutionary models leads to unstable recommendation accuracy. In addition, the collaborative filtering method of GCN does not take into account the dynamic evolution law of graph networks. Based on this, this research adopts GCN to train the initial embedding of the dynamic evolution model to perform collaborative filtering recommendation. First of all, a heterogeneous graph network is constructed by applying explicit feedback information (rating scores) of users. Secondly, the embedding of users and items are propagated through the dynamic evolution model. Then, the final embedding is obtained by weighting the embedding of each layer, and the scores are predicted. Finally, according to the Adam optimizer, the initial embedding of the dynamic evolution model is trained in the form of mini-batch to minimize the loss function. Experimental results show that the proposed algorithm is superior to several compared excellent algorithms in recommendation performance.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127568859","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 : 2021-10-01DOI: 10.1109/NaNA53684.2021.00084
Yubaraj Gautam, Kazuhiko Sato, B. P. Gautam, N. Shiratori
A software-defined network (SDN) is an emerging network technology that can augment the data plane with a control plane using programming techniques. However, there are certain security challenges that must be addressed to achieve secure communication. Flooding attacks have been one of the most common threats on the internet since the last decade. They have become a challenge for SDNs as well. To address this issue, we have proposed a novel firewall application, which has been developed based on multiple stages of the packet filtering technique, and provide layer-based security and a flood attack prevention system. The proposed application mainly comprises two security entities—one provides layer-based security, while the other has been designed specifically for preventing and mitigating flooding attacks. The layer-based packet filtering technique, which has been applied in the proposed system, filters all types of unwanted packets using the layer (layers 2, 3, and 4)-based packet header entity. Meanwhile, the flooding attack prevention system functions by counting the number of packets and their sizes. The proposed solution was tested for different attack scenarios; it was able to prevent 74.12% of flooding attacks, while conducting flooding attacks in SDN.
{"title":"Novel Firewall Application for Mitigating Flooding Attacks on an SDN Network","authors":"Yubaraj Gautam, Kazuhiko Sato, B. P. Gautam, N. Shiratori","doi":"10.1109/NaNA53684.2021.00084","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00084","url":null,"abstract":"A software-defined network (SDN) is an emerging network technology that can augment the data plane with a control plane using programming techniques. However, there are certain security challenges that must be addressed to achieve secure communication. Flooding attacks have been one of the most common threats on the internet since the last decade. They have become a challenge for SDNs as well. To address this issue, we have proposed a novel firewall application, which has been developed based on multiple stages of the packet filtering technique, and provide layer-based security and a flood attack prevention system. The proposed application mainly comprises two security entities—one provides layer-based security, while the other has been designed specifically for preventing and mitigating flooding attacks. The layer-based packet filtering technique, which has been applied in the proposed system, filters all types of unwanted packets using the layer (layers 2, 3, and 4)-based packet header entity. Meanwhile, the flooding attack prevention system functions by counting the number of packets and their sizes. The proposed solution was tested for different attack scenarios; it was able to prevent 74.12% of flooding attacks, while conducting flooding attacks in SDN.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126317039","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 : 2021-10-01DOI: 10.1109/NaNA53684.2021.00021
Hui Wang, Yani Han, Shaojing Yang, Anxiao Song, Tao Zhang
Federated Learning (FL) shows its great vitality for terminal devices of Internet of Things (IoT) in privacy protection. However, the amount of data on each device in IoT are imbalanced which makes the global training model rarely effective. Although Generative Adversarial Network (GAN) can generate data to alleviate the above problem, it has the characteristic of training instability and still carries the risk of privacy breach. In this paper, we propose a novel privacy-preserving federated GAN framework, named P-FedGAN, to train a federated generative model with privacy protection function. Each device uses the trained model to generate enough synthetic data to replace sensitive data to train desired model that can complete typical data analysis tasks. We carry out several sets of experiments to test the validity of proposed framework. The results of the experiments indicate that proposed framework meets differential privacy constraints and produces high-quality model utility compared to federated average algorithm simultaneously.
{"title":"Privacy-Preserving Federated Generative Adversarial Network for IoT","authors":"Hui Wang, Yani Han, Shaojing Yang, Anxiao Song, Tao Zhang","doi":"10.1109/NaNA53684.2021.00021","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00021","url":null,"abstract":"Federated Learning (FL) shows its great vitality for terminal devices of Internet of Things (IoT) in privacy protection. However, the amount of data on each device in IoT are imbalanced which makes the global training model rarely effective. Although Generative Adversarial Network (GAN) can generate data to alleviate the above problem, it has the characteristic of training instability and still carries the risk of privacy breach. In this paper, we propose a novel privacy-preserving federated GAN framework, named P-FedGAN, to train a federated generative model with privacy protection function. Each device uses the trained model to generate enough synthetic data to replace sensitive data to train desired model that can complete typical data analysis tasks. We carry out several sets of experiments to test the validity of proposed framework. The results of the experiments indicate that proposed framework meets differential privacy constraints and produces high-quality model utility compared to federated average algorithm simultaneously.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125878715","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：