Detection of Cache Pollution Attack Based on Federated Learning in Ultra-Dense Network

Detection of Cache Pollution Attack Based on Federated Learning in Ultra-Dense Network
复制标题

超密集网络中基于联邦学习的缓存污染攻击检测

DOI:
10.1016/j.cose.2022.102965
复制
发表时间:
2022-10
影响因子:
5.6
通讯作者:
吴国伟
吴国伟
中科院分区:
计算机科学3区
文献类型:
--
作者:
姚琳;李佳;邓镜;吴国伟

文献摘要

参考文献

相似文献

超密集网络(UDN)作为5G的关键技术之一,旨在通过部署密集的小型基站(SBS)将当前4G网络的单位面积容量提高1,000倍。为了减少回程链路上的流量,以内容为中心的网络(CCN)作为一种很有前途的网络架构,近年来已被应用于UDN。然而,它的网络缓存机制受到缓存污染攻击(CPA),攻击者的目的是占用有限的缓存空间与不受欢迎的内容。现有的研究集中在静态网络不能直接用于动态UDN场景。在本文中,我们提出了一种基于联邦学习的CPA检测和防御方案,其中CPA是由多个SBS的合作。首先,每个SBS可以基于距离相似性和负载相似性的度量来构建或加入集群。然后,每个簇头作为工作节点训练本地分类器,以基于簇内的统计信息来检测CPA。宏基站聚合所有局部模型以生成用于所有SBS的改进的全局分类器。在我们的方案中,联邦学习作为分布式机器学习的一种特殊情况,允许每个簇头独立地训练本地数据,即使它是非独立的。或不平衡。仿真结果表明,我们的计划优于检测率,缓存命中率,访问延迟,和虚警率与其他国家的最先进的计划相比。
Ultra-Dense Network (UDN) as one of the key technologies of 5G aims to increase the capacity per area of the current 4G network by 1,000-fold through the deployment of dense Small Base Stations (SBSs). To reduce the traffic on backhaul links, Content-Centric Networking (CCN) as a promising network architecture has been applied to UDN recently. However, its in-network caching mechanism is subject to Cache Pollution Attack (CPA), where attackers aim to occupy limited caching space with unpopular contents. Existing studies focusing on the static networks cannot be directly used in dynamic UDN scenarios. In this paper, we propose a detection and defense scheme of CPA based on federated learning, where CPA is determined by the cooperation of multiple SBSs. First, each SBS can build or join a cluster based on the metrics of distance similarity and load similarity. Then, each cluster head as the working node trains the local classifier to detect CPA based on the statistics within the cluster. The macro base station aggregates all the local models to generate an improved global classifier for all the SBSs. In our scheme, federated learning as a special case of distributed machine learning allows each cluster head to independently train the local data even when it is non-i.i.d. or unbalanced. Simulation results show that our scheme outperforms in terms of detection ratio, cache hit ratio, access delay, and false alarm ratio compared with other state-of-the-art schemes.
DOI: 10.48550/arxiv.1806.00582
发表时间: 2018-06
期刊: ArXiv
影响因子: --
作者:
Yue Zhao;Meng Li;Liangzhen Lai;Naveen Suda;Damon Civin;V. Chandra
通讯作者: Yue Zhao;Meng Li;Liangzhen Lai;Naveen Suda;Damon Civin;V. Chandra
DOI: 10.23919/wiopt.2018.8362880
发表时间: 2018-05
期刊: 2018 16th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)
影响因子: --
作者:
G. Haßlinger;Juho Heikkinen;Konstantinos Ntougias;Frank Hasslinger;O. Hohlfeld
通讯作者: G. Haßlinger;Juho Heikkinen;Konstantinos Ntougias;Frank Hasslinger;O. Hohlfeld
DOI: 10.1016/j.comnet.2015.01.020
发表时间: 2015-04
期刊: Comput. Networks
影响因子: --
作者:
Amin Karami;Manel Guerrero Zapata
通讯作者: Amin Karami;Manel Guerrero Zapata
DOI: 10.1109/icc.2012.6363885
发表时间: 2012-06
期刊: 2012 IEEE International Conference on Communications (ICC)
影响因子: --
作者:
Hyundo Park;I. Widjaja;Heejo Lee
通讯作者: Hyundo Park;I. Widjaja;Heejo Lee
DOI: 10.1109/icccn.2016.7568592
发表时间: 2016-08
期刊: 2016 25th International Conference on Computer Communication and Networks (ICCCN)
影响因子: --
作者:
Wei Yu;Hansong Xu;Hanlin Zhang;D. Griffith;N. Golmie
通讯作者: Wei Yu;Hansong Xu;Hanlin Zhang;D. Griffith;N. Golmie