2021 International Conference on Networking and Network Applications (NaNA)最新文献_第4页

Fatigue Detection Technology for Online Learning 在线学习疲劳检测技术

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00054

Junjie Lu, Chao Qi

引用次数: 1

TPLI:A Traceable Privacy-preserving Logistics Information Scheme via Blockchain TPLI:基于区块链的可追溯隐私保护物流信息方案

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00066

Xiaoguo Lin, Pujie Jing, Chuntang Yu, Xia Feng

引用次数: 2

Wet Aggregate Stability Predicting of Soil in Multiple Land-Uses Based on Support Vector Machine 基于支持向量机的多种土地利用土壤湿团聚体稳定性预测

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00097

Ruizhi Zhai, Deshun Yin, Jian-ping Wang, Lili Yuan, Ziheng Shangguan

引用次数: 0

CLSDRL:A routing optimization method for traffic feature extraction 一种用于交通特征提取的路由优化方法

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00052

Hong Xia, Jianguo Li, Yanping Chen, Ning Lv, Zhongmin Wang, Qingyi Dong

引用次数: 0

Wiretapping or Jamming: On Eavesdropper Attacking Strategy in mmWave Ad Hoc Networks 窃听或干扰:毫米波自组织网络中的窃听攻击策略

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00010

Yuanyu Zhang, Ji He, Qianyue Qu, Zhiwei Zhang

{"title":"Wiretapping or Jamming: On Eavesdropper Attacking Strategy in mmWave Ad Hoc Networks","authors":"Yuanyu Zhang, Ji He, Qianyue Qu, Zhiwei Zhang","doi":"10.1109/NaNA53684.2021.00010","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00010","url":null,"abstract":"Millimeter-meter (mmWave) communication is difficult to wiretap due to the short transmission range and highly directional transmitting antennas, meaning that wiretapping is not the best attacking strategy for eavesdroppers in mmWave networks. However, eavesdroppers can maximize their payoffs by opportunistically switching between the wiretapping attack and other attacks, leading to a more interesting and hazardous attack. This paper, for the first time, investigates such selective eavesdropper attacking strategies, i.e., the selection between the wiretapping attack and another representative attack (jamming), in mmWave ad hoc networks. We first propose two attacking strategies, i.e., Random Attacking (RA), where eavesdroppers independently and randomly select their attack patterns with a common probability, and Selective Attacking based on Distances (SA-D), where each eavesdropper independently conducts the selection based on its smallest distances to transmitters and receivers, respectively. Using tools from stochastic geometry, we then perform theoretical modelling on the secrecy transmission capacity (STC) of the network under both strategies. Finally, we provide extensive numerical results to illustrate the impacts of attacking parameters on the network STC performance under the proposed strategies.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"47 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":"124831853","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}

引用次数: 1

Detecting Http Flooding Attacks Based on Uniform Model 基于统一模型的Http泛洪攻击检测

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00024

D. Nashat, S. Khairy

引用次数: 2

Graph Neural Networks for Privacy-Preserving Recommendation with Secure Hardware 基于图神经网络的安全硬件隐私保护推荐

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00075

Sisong Ru, Bin Zhang, Yixin Jie, Chi Zhang, Lingbo Wei, Chengjie Gu

{"title":"Graph Neural Networks for Privacy-Preserving Recommendation with Secure Hardware","authors":"Sisong Ru, Bin Zhang, Yixin Jie, Chi Zhang, Lingbo Wei, Chengjie Gu","doi":"10.1109/NaNA53684.2021.00075","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00075","url":null,"abstract":"Local differential privacy (LDP) is widely used in graph neural networks (GNNs) for recommendation to protect users’ privacy. However, existing LDP-based GNNs usually introduce too much noise caused by the untrusted servers and result in poor model accuracy. The emergence of trusted execution environments such as intel SGX can guarantee code integrity and data confidentiality, and lead a new direction in differential privacy. In this paper, we propose a federated GNN recommendation system based on SGX and DP, which converts the LDP model into a central differential privacy (CDP) model without a trusted server. Specifically, in our scheme, the SGX runs differentially private computations on the data and reveals the results, which introduces less noise while achieving the same privacy protection level compared with LDP. And in order to address the privacy concerns caused by side channel attacks in SGX, we additionally use homomorphic encryption to encrypt the data before uploading, so that even if SGX is breached, the adversary could only access the ciphertext, not the plaintext. We prove that our algorithm satisfies (epsilon, delta) -CDP for data owners and conduct experiments on several real-world datasets. The result shows that our method is outperforming existing LDP-based GNN recommendation systems.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"135 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":"122646523","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}

引用次数: 4

Dynamic Overhead Queue-based Efficient Service Delivery at Edge for Adaptive Live Streaming 基于动态开销队列的自适应直播边缘高效服务交付

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00036

Zichen Feng, Changqiao Xu, Han Xiao, Y. Jia, Zhongyi Ding, Zhaoyang Liu

{"title":"Dynamic Overhead Queue-based Efficient Service Delivery at Edge for Adaptive Live Streaming","authors":"Zichen Feng, Changqiao Xu, Han Xiao, Y. Jia, Zhongyi Ding, Zhaoyang Liu","doi":"10.1109/NaNA53684.2021.00036","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00036","url":null,"abstract":"The live broadcast business has developed rapidly in recent years, but low latency, smoothness, and high user quality of experience (QoE) are still the problems that we need to solve. At the same time, the arise of edge computing has made up for the lack of traditional cloud computing in live broadcast services and brought low-latency effects, but also brought a heavy burden to the edge network, making edge load balancing an important issue to be solved urgently. Meanwhile, the real-time and low-latency characteristics of live broadcast put forward higher requirements on the network, which increases the difficulty of load balancing optimization. Therefore, to cope with the development trend of adaptive live streaming and improve the QoE, this article first proposes an adaptive live streaming transmission framework under the edge network, which integrates edge service clusters, multicast, and client adaptive bitrate(ABR) algorithms. Then, we proposed a load optimization scheme for edge service clusters, focusing on the dynamics of load and transmission costs. According to the two factors directly affected by the ABR algorithm, i.e. edge server CPU load and bandwidth overhead, The dynamic overhead queue load-balancing algorithm is proposed. Compared with the other three load optimization algorithms, the simulation results show the superiority of our scheme in term of load balancing and overhead.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"62 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":"115528881","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}

引用次数: 0

On the Robustness of Complex System With Percolation Theory Under Node Attack 节点攻击下基于渗透理论的复杂系统鲁棒性研究

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00070

Xiaoteng Yang, Wenbo Zhang, Bo Liu, Hong Su

{"title":"On the Robustness of Complex System With Percolation Theory Under Node Attack","authors":"Xiaoteng Yang, Wenbo Zhang, Bo Liu, Hong Su","doi":"10.1109/NaNA53684.2021.00070","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00070","url":null,"abstract":"Many complex systems in life can be described by networks. Each component in the system can be represented by vertices, and the connections between components can be represented by edges. One of the most important problems in a complex network system is the ability of the system to maintain its functions when some components fail, which can be understood as the impact of the failure of complex network nodes on the overall connectivity of the network. In this paper, through the percolation theory, the network node random failure percolation threshold is obtained. For different public data sets, different attack methods and attack strategies are used to observe the change of the largest connected component in the network with the removal of nodes. Experiments show that target attacks are more harmful to the network than random attacks. At the same time, when the network faces target attacks, sequential targeted attacks are more destructive than simultaneous targeted attacks. For different attack strategies, in most cases, the attack strategies of degree and eigenvector are more destructive to the network, and reach the network’s percolation threshold faster.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"113 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":"132557547","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}

引用次数: 1

A Recommendation Scheme with Reputation-Based Incentive Mechanism on Consortium Blockchain 基于声誉激励机制的联盟区块链推荐方案

2021 International Conference on Networking and Network Applications (NaNA) Pub Date : 2021-10-01 DOI: 10.1109/NaNA53684.2021.00061

Qingyi Ye, Tingting Zhao, Guo Sun, Xia Feng

{"title":"A Recommendation Scheme with Reputation-Based Incentive Mechanism on Consortium Blockchain","authors":"Qingyi Ye, Tingting Zhao, Guo Sun, Xia Feng","doi":"10.1109/NaNA53684.2021.00061","DOIUrl":"https://doi.org/10.1109/NaNA53684.2021.00061","url":null,"abstract":"Aiming at the problem of privacy leakage and lack of trust in centralized recommendation system architecture, we propose a recommendation scheme with reputation-based incentive mechanism on consortium blockchain, which uses the auditable and transparent feature of consortium blockchain to enhance the credibility of the recommendation system. Multiple users are allowed to participate in the recommendation process fairly through the certification before joining the blockchain network. Besides, the scheme introduces a reputation-based incentive mechanism, which can curb users’ malicious behaviors and attract more users to participate in the recommendation process, thus optimizing the recommendation results. Then, we design and implement an education resources recommendation system based on the proposed scheme, which provides a new solution idea for the design of highly credible recommendation systems. Finally, the experimental analysis of the proposed scheme shows that it can achieve fair and credible recommendations and significantly improve the accuracy of the recommendation results.","PeriodicalId":414672,"journal":{"name":"2021 International Conference on Networking and Network Applications (NaNA)","volume":"58 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":"131126770","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}

引用次数: 5