Pub Date : 2021-10-01DOI: 10.1109/NaNA53684.2021.00089
Kenan Qin, Yihui Zhou, Bo Tian, Rui Wang
Anomaly detection in attributed networks is to find nodes that deviate from the behavior patterns of most nodes, which is widely used in social network false account detection or network intrusion detection and so on. However, most existing methods only focus on one aspect of network either network structure or node attributes, ignoring the interaction between network structure and node attributes. Meanwhile, they regard reconstruction error as node anomaly score, which lacks considering the other factors for computing score. Therefore, in this paper, we propose a method for attributed network anomaly detection based on an autoencoder considering the node attention mechanism and an anomaly score generator. The autoencoder considers not only network structure but also node attributes to obtain a higher-quality embedded representation. Meanwhile, the decoder reconstructs the adjacency matrix and calculates the reconstruction error. The anomaly score generator uses a multi-layer perceptron (MLP) as the basic framework. In addition, in order to better consider the calculation of the node anomaly score by the reconstruction error, we concatenate the reconstruction error, reconstruct the residual direction vector and embedding vector to construct input vector for training MLP. At last, the final output is node anomaly score, and anomaly detection achieved. Experiments on three real-world datasets prove the effectiveness of our method.
{"title":"AttentionAE: Autoencoder for Anomaly Detection in Attributed Networks","authors":"Kenan Qin, Yihui Zhou, Bo Tian, Rui Wang","doi":"10.1109/NaNA53684.2021.00089","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00089","url":null,"abstract":"Anomaly detection in attributed networks is to find nodes that deviate from the behavior patterns of most nodes, which is widely used in social network false account detection or network intrusion detection and so on. However, most existing methods only focus on one aspect of network either network structure or node attributes, ignoring the interaction between network structure and node attributes. Meanwhile, they regard reconstruction error as node anomaly score, which lacks considering the other factors for computing score. Therefore, in this paper, we propose a method for attributed network anomaly detection based on an autoencoder considering the node attention mechanism and an anomaly score generator. The autoencoder considers not only network structure but also node attributes to obtain a higher-quality embedded representation. Meanwhile, the decoder reconstructs the adjacency matrix and calculates the reconstruction error. The anomaly score generator uses a multi-layer perceptron (MLP) as the basic framework. In addition, in order to better consider the calculation of the node anomaly score by the reconstruction error, we concatenate the reconstruction error, reconstruct the residual direction vector and embedding vector to construct input vector for training MLP. At last, the final output is node anomaly score, and anomaly detection achieved. Experiments on three real-world datasets prove the effectiveness of our method.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"14 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":"123046440","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/NaNA53684.2021.00078
Zhihao Xu, Kezhang Lin, Zhiwei Zhang, Wangzhe Xu, K. Liu, Bin Wang, Xinghui Zhu, Jiadong Chen
Nowadays, with the development of digital image, video, and other multimedia visualization techniques, electronic screens are ubiquitous in various scenarios, and these screens provide vivid communication and presentation methods. Unfortunately, at the same time, the security and safety defenders have noticed that it is more and more difficult to prevent people from photographing the contents on the screens, especially when the photographic equipment is undergoing miniaturization and intelligentization, and that promotes the information and privacy leakage inevitably. There are plenty of technical solutions that have been proposed previously, but few of the exiting schemes are feasible for daily and widespread applications because most of them require some additional and customized hardware to be mounted on the screens or audiences. Therefore, in this paper, we propose an intelligent content protection scheme for videos on screens, which is designed to prevent audiences from photographing the entire picture of the screen while having no observable influence for direct observation with naked eyes. Furthermore, our experiments demonstrate that, for the 1080P and 60 fps videos on ordinary LCD screens, our scheme outperforms the existing schemes in terms of occlusion rate, effective distance and so on.
{"title":"You Can See, But You Cannot Photograph: An Intelligent Content Protection Scheme for Videos on Screens","authors":"Zhihao Xu, Kezhang Lin, Zhiwei Zhang, Wangzhe Xu, K. Liu, Bin Wang, Xinghui Zhu, Jiadong Chen","doi":"10.1109/NaNA53684.2021.00078","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00078","url":null,"abstract":"Nowadays, with the development of digital image, video, and other multimedia visualization techniques, electronic screens are ubiquitous in various scenarios, and these screens provide vivid communication and presentation methods. Unfortunately, at the same time, the security and safety defenders have noticed that it is more and more difficult to prevent people from photographing the contents on the screens, especially when the photographic equipment is undergoing miniaturization and intelligentization, and that promotes the information and privacy leakage inevitably. There are plenty of technical solutions that have been proposed previously, but few of the exiting schemes are feasible for daily and widespread applications because most of them require some additional and customized hardware to be mounted on the screens or audiences. Therefore, in this paper, we propose an intelligent content protection scheme for videos on screens, which is designed to prevent audiences from photographing the entire picture of the screen while having no observable influence for direct observation with naked eyes. Furthermore, our experiments demonstrate that, for the 1080P and 60 fps videos on ordinary LCD screens, our scheme outperforms the existing schemes in terms of occlusion rate, effective distance and so on.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"35 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":"115986952","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/NaNA53684.2021.00085
Ke Zhao, Limei Peng
This paper proposes using UAVs as auxiliary flying relays between IoT access points (APs) and terrestrial base stations/satellites. Specifically, we consider the 3D deployment of multiple UAVs above a given area of APs, aiming at providing efficient services to the APs while optimizing the overall performance of UAVs. In particular, we aim to minimize the number of required UAV flights when serving the APs within a demanded time, which is constrained by the total available power of UAVs, and maximize the total number of successfully served APs. For this, we propose an integer linear programming (ILP) model that can achieve the above goals by adjusting the UAV hovering heights in the appropriately selected coordinates. The proposed ILP model is evaluated when considering interference among the multiple UAVs and compared with the schemes based on fixed heights. The numerical results show that the proposed ILP model can automatically adjust the flying height of UAVs to reduce the flights when complying with the constraints of the signal-to-interference-noise ratio (SINR) threshold and the number of APs to be served.
{"title":"UAV Deployment with Flexible Height Under SINR Constraint","authors":"Ke Zhao, Limei Peng","doi":"10.1109/NaNA53684.2021.00085","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00085","url":null,"abstract":"This paper proposes using UAVs as auxiliary flying relays between IoT access points (APs) and terrestrial base stations/satellites. Specifically, we consider the 3D deployment of multiple UAVs above a given area of APs, aiming at providing efficient services to the APs while optimizing the overall performance of UAVs. In particular, we aim to minimize the number of required UAV flights when serving the APs within a demanded time, which is constrained by the total available power of UAVs, and maximize the total number of successfully served APs. For this, we propose an integer linear programming (ILP) model that can achieve the above goals by adjusting the UAV hovering heights in the appropriately selected coordinates. The proposed ILP model is evaluated when considering interference among the multiple UAVs and compared with the schemes based on fixed heights. The numerical results show that the proposed ILP model can automatically adjust the flying height of UAVs to reduce the flights when complying with the constraints of the signal-to-interference-noise ratio (SINR) threshold and the number of APs to be served.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"31 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":"117300450","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/NaNA53684.2021.00023
Yu He, Youliang Tian, Huanliang Xu
In order to solve the problem of difficult verification of query results in searchable encryption, we used the idea of Shamir-secret sharing, combined with game theory, to construct a randomly verifiable multi-cloud server searchable encryption scheme to achieve the correctness of the query results in the cloud storage environment verify. Firstly, we using the Shamir-secret sharing technology, the encrypted data is stored on each independent server to construct a multi-cloud server model to realize the secure distributed storage and efficient query of data. Secondly, combined with game theory, a game tree of query server and verification server is constructed to ensure honesty while being efficient, and solve the problem of difficulty in returning search results to verify under the multi-cloud server model. Finally, security analysis and experimental analysis show that this solution effectively protects data privacy while significantly reducing retrieval time.
{"title":"Random verifiable multi-server searchable encryption scheme","authors":"Yu He, Youliang Tian, Huanliang Xu","doi":"10.1109/NaNA53684.2021.00023","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00023","url":null,"abstract":"In order to solve the problem of difficult verification of query results in searchable encryption, we used the idea of Shamir-secret sharing, combined with game theory, to construct a randomly verifiable multi-cloud server searchable encryption scheme to achieve the correctness of the query results in the cloud storage environment verify. Firstly, we using the Shamir-secret sharing technology, the encrypted data is stored on each independent server to construct a multi-cloud server model to realize the secure distributed storage and efficient query of data. Secondly, combined with game theory, a game tree of query server and verification server is constructed to ensure honesty while being efficient, and solve the problem of difficulty in returning search results to verify under the multi-cloud server model. Finally, security analysis and experimental analysis show that this solution effectively protects data privacy while significantly reducing retrieval time.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"15 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":"126181175","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/NaNA53684.2021.00067
Chen Chong, Zou Ping
In recent years, the vulnerabilities of network applications have frequently appeared, which has made the mining of vulnerabilities more and more concerned in recent years, because once the vulnerabilities caused by network applications are exploited, they will cause high-level security problems and have a big impact. AFL (American Fuzzy Lop) is a mutation-based fuzzing technology, and it is also one of the most popular and effective fuzzing tools. It has good performance and performance in mining vulnerabilities. Aiming at network applications and based on AFL, this paper optimizes the framework’s deficiencies in seed generation and seed selection, and designs and implements a higher-performance vulnerability detection tool. In the aspect of seed generation, the PSO (particle swarm optimization) algorithm is used to modify some related algorithms in the mutation stage of AFL to optimize the operator selection process in this stage. Instead of using the fixed selection algorithm, the current operator environment and the previous operator environment are considered in each operator selection to make a decision. In the aspect of seed selection, we model the number of mutation times needed by the seeds to generate new paths, give priority to the seeds that execute low-frequency paths, and give them higher mutation times, that is, the power of the seeds, so as to improve the utilization efficiency of the seeds and obtain more path coverage.
{"title":"Network application vulnerability detection based on fuzzing technology","authors":"Chen Chong, Zou Ping","doi":"10.1109/NaNA53684.2021.00067","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00067","url":null,"abstract":"In recent years, the vulnerabilities of network applications have frequently appeared, which has made the mining of vulnerabilities more and more concerned in recent years, because once the vulnerabilities caused by network applications are exploited, they will cause high-level security problems and have a big impact. AFL (American Fuzzy Lop) is a mutation-based fuzzing technology, and it is also one of the most popular and effective fuzzing tools. It has good performance and performance in mining vulnerabilities. Aiming at network applications and based on AFL, this paper optimizes the framework’s deficiencies in seed generation and seed selection, and designs and implements a higher-performance vulnerability detection tool. In the aspect of seed generation, the PSO (particle swarm optimization) algorithm is used to modify some related algorithms in the mutation stage of AFL to optimize the operator selection process in this stage. Instead of using the fixed selection algorithm, the current operator environment and the previous operator environment are considered in each operator selection to make a decision. In the aspect of seed selection, we model the number of mutation times needed by the seeds to generate new paths, give priority to the seeds that execute low-frequency paths, and give them higher mutation times, that is, the power of the seeds, so as to improve the utilization efficiency of the seeds and obtain more path coverage.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"35 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":"127255217","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 extraction and use of features from the raw sensor data plays an extremely crucial role in determining the recognition performance of an activity recognizer. Existing studies aim to train an accurate prediction model by extracting different features, however, few of them systematically investigate the power of features from different domains when they are used separately or jointly. To this end, we conduct a comparative study on multi-domain feature extraction for human activity recognition. Specifically, we first extract features from the time-, frequency-, and wavelet-domains, and then use different combinations of the three domain features to build activity recognizers. Finally, comparative experiments are performed on two activity recognition datasets and four classification models are used to avoid selection bias. Results indicate the superiority of using time-domain or frequency-domain features over wavelet features in terms of prediction performance and also show that the simultaneous use of multi-domain features generally generalizes better across datasets and classifiers, indicating that they, to a certain extent, contain complementary feature information.
{"title":"Multi-domain Feature Extraction for Human Activity Recognition Using Wearable Sensors","authors":"Aiguo Wang, Yue Meng, Jinjun Liu, Shenghui Zhao, Guilin Chen","doi":"10.1109/NaNA53684.2021.00051","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00051","url":null,"abstract":"The extraction and use of features from the raw sensor data plays an extremely crucial role in determining the recognition performance of an activity recognizer. Existing studies aim to train an accurate prediction model by extracting different features, however, few of them systematically investigate the power of features from different domains when they are used separately or jointly. To this end, we conduct a comparative study on multi-domain feature extraction for human activity recognition. Specifically, we first extract features from the time-, frequency-, and wavelet-domains, and then use different combinations of the three domain features to build activity recognizers. Finally, comparative experiments are performed on two activity recognition datasets and four classification models are used to avoid selection bias. Results indicate the superiority of using time-domain or frequency-domain features over wavelet features in terms of prediction performance and also show that the simultaneous use of multi-domain features generally generalizes better across datasets and classifiers, indicating that they, to a certain extent, contain complementary feature information.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"32 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":"122098996","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/NaNA53684.2021.00076
Yue He, Hui Li, Yiming Li, Qiang Wu, Yuefeng Ji, Rentao Gu, Shaobin Fan
With the rapid development of information technology, the society’s demand for information technology talents has become particularly high; how colleges and universities devote themselves to cultivating professional information technology talents is an important direction at present. However, the teacher’s evaluation method stays at the exam-oriented education. In the university education, in order to help students with basic professional knowledge to learn more professional knowledge and skills, and to help teachers understand the characteristics of students more objectively, this article discusses how to improve the existing teaching environment and simulation teaching mode. A simulation teaching platform for the “Intelligent Information Network” course is designed with multiple modules for complex network construction. Through the online network simulation teaching platform and the feedback obtained from the platform’s use, different students’ different problems can be found objectively, and the combination of theory and engineering, the combination of new and old knowledge, and the simplicity of complex software can be realized.
{"title":"Exploration of Simulation Teaching Mode for Intelligent Information Network Course","authors":"Yue He, Hui Li, Yiming Li, Qiang Wu, Yuefeng Ji, Rentao Gu, Shaobin Fan","doi":"10.1109/NaNA53684.2021.00076","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00076","url":null,"abstract":"With the rapid development of information technology, the society’s demand for information technology talents has become particularly high; how colleges and universities devote themselves to cultivating professional information technology talents is an important direction at present. However, the teacher’s evaluation method stays at the exam-oriented education. In the university education, in order to help students with basic professional knowledge to learn more professional knowledge and skills, and to help teachers understand the characteristics of students more objectively, this article discusses how to improve the existing teaching environment and simulation teaching mode. A simulation teaching platform for the “Intelligent Information Network” course is designed with multiple modules for complex network construction. Through the online network simulation teaching platform and the feedback obtained from the platform’s use, different students’ different problems can be found objectively, and the combination of theory and engineering, the combination of new and old knowledge, and the simplicity of complex software can be realized.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"101 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":"123244878","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/NaNA53684.2021.00095
Xinhong Hei, Hao Zhang, Wenjiang Ji, Yichuan Wang, Lei Zhu, Yuan Qiu
Risk prediction is one of the most important tasks in assistant and automatic driving. In recent years, by the help of VANET and various sensors in the cars, the status of cars and roads can be collected in real time and used for data-driven based driving risk prediction. However, it is challenging to predict the driving risk due to the complex relationship between multiple environment factors like location, weather, time etc. Thus, a deep learning model ConvCatb was proposed in this paper, which improves the attention mechanism to the traditional Convolutional Neural Networks, and combines the CatBoost algorithm to predict the current driving safety. The main idea is to emphasize the combination relationship between driving environment features through Non-local attention mechanism, and then use CatBoost to replace the softmax of CNN for classification. Finally, the experiment results show that the ConvCatb achieved superiorities in accuracy and F1-score, compared with existing schemes.
{"title":"ConvCatb: An Attention-based CNN-CATBOOST Risk Prediction Model for Driving Safety","authors":"Xinhong Hei, Hao Zhang, Wenjiang Ji, Yichuan Wang, Lei Zhu, Yuan Qiu","doi":"10.1109/NaNA53684.2021.00095","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00095","url":null,"abstract":"Risk prediction is one of the most important tasks in assistant and automatic driving. In recent years, by the help of VANET and various sensors in the cars, the status of cars and roads can be collected in real time and used for data-driven based driving risk prediction. However, it is challenging to predict the driving risk due to the complex relationship between multiple environment factors like location, weather, time etc. Thus, a deep learning model ConvCatb was proposed in this paper, which improves the attention mechanism to the traditional Convolutional Neural Networks, and combines the CatBoost algorithm to predict the current driving safety. The main idea is to emphasize the combination relationship between driving environment features through Non-local attention mechanism, and then use CatBoost to replace the softmax of CNN for classification. Finally, the experiment results show that the ConvCatb achieved superiorities in accuracy and F1-score, compared with existing schemes.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"46 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":"126260225","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/NaNA53684.2021.00053
Yusuke Noda, B. P. Gautam
Routing optimization is an essential computational mechanism for Internet service providers seeking to optimize network performance and traffic delivery. In order to address the problems of routing optimization, various types of routing optimization algorithms are reported till date. Genetic algorithm (GA) is one of the most popular meta-heuristic combinatorial optimization algorithms, which has been widely used for various optimization problems including network route optimization. In this study, we demonstrated how to find an optimized network path between designated source and destination in a given network with 95 nodes and 200 links using the GA. Our result shows that the GA with the lower mutation probability for reducing the wasteful search space is a comprehensive approach in this study in terms of computational challenges and routing optimization. Our investigation concludes that the GA is an efficient and alternative method of finding an optimal route so as to achieve the desired network performance and to reduce congestion control.
{"title":"A Proposal of Large Scale Network Route Optimization Technique Based on Genetic Algorithm","authors":"Yusuke Noda, B. P. Gautam","doi":"10.1109/NaNA53684.2021.00053","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00053","url":null,"abstract":"Routing optimization is an essential computational mechanism for Internet service providers seeking to optimize network performance and traffic delivery. In order to address the problems of routing optimization, various types of routing optimization algorithms are reported till date. Genetic algorithm (GA) is one of the most popular meta-heuristic combinatorial optimization algorithms, which has been widely used for various optimization problems including network route optimization. In this study, we demonstrated how to find an optimized network path between designated source and destination in a given network with 95 nodes and 200 links using the GA. Our result shows that the GA with the lower mutation probability for reducing the wasteful search space is a comprehensive approach in this study in terms of computational challenges and routing optimization. Our investigation concludes that the GA is an efficient and alternative method of finding an optimal route so as to achieve the desired network performance and to reduce congestion control.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"138 3 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":"130892898","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/NaNA53684.2021.00025
Chen Yang, Zhen Jia, Shundong Li
With the popularization of mobile communication and sensing equipment, as well as the rapid development of location-aware technology and wireless communication technology, LBSs(Location-based services) bring convenience to people’s lives and enable people to arrange activities more efficiently and reasonably. It can provide more flexible LBS proximity detection query, which has attracted widespread attention in recent years. However, the development of proximity detection query still faces many severe challenges including query information privacy. For example, when users want to ensure their location privacy and data security, they can get more secure location-based services. In this article, we propose an efficient and privacy-protecting proximity detection framework based on location services: PD(Proximity Detection). Through PD, users can query the range of arbitrary polygons and obtain accurate LBS results. Specifically, based on homomorphic encryption technology, an efficient PRQ(polygon range query) algorithm is constructed. With the help of PRQ, PD, you can obtain accurate polygon range query results through the encryption request and the services provided by the LAS(LBS Agent Server) and the CS(Cloud Server). In addition, the query privacy of the queryer and the information of the data provider are protected. The correctness proof and performance analysis show that the scheme is safe and feasible. Therefore, our scheme is suitable for many practical applications.
{"title":"Privacy-Preserving Proximity Detection Framework for Location-Based Services","authors":"Chen Yang, Zhen Jia, Shundong Li","doi":"10.1109/NaNA53684.2021.00025","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00025","url":null,"abstract":"With the popularization of mobile communication and sensing equipment, as well as the rapid development of location-aware technology and wireless communication technology, LBSs(Location-based services) bring convenience to people’s lives and enable people to arrange activities more efficiently and reasonably. It can provide more flexible LBS proximity detection query, which has attracted widespread attention in recent years. However, the development of proximity detection query still faces many severe challenges including query information privacy. For example, when users want to ensure their location privacy and data security, they can get more secure location-based services. In this article, we propose an efficient and privacy-protecting proximity detection framework based on location services: PD(Proximity Detection). Through PD, users can query the range of arbitrary polygons and obtain accurate LBS results. Specifically, based on homomorphic encryption technology, an efficient PRQ(polygon range query) algorithm is constructed. With the help of PRQ, PD, you can obtain accurate polygon range query results through the encryption request and the services provided by the LAS(LBS Agent Server) and the CS(Cloud Server). In addition, the query privacy of the queryer and the information of the data provider are protected. The correctness proof and performance analysis show that the scheme is safe and feasible. Therefore, our scheme is suitable for many practical applications.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"4 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":"134083552","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：