Named Data Networking(NDN)is one of the most excellent future Internet architectures and every router in NDN has the capacity of caching contents passing by.It greatly reduces network traffic and improves the speed of...Named Data Networking(NDN)is one of the most excellent future Internet architectures and every router in NDN has the capacity of caching contents passing by.It greatly reduces network traffic and improves the speed of content distribution and retrieval.In order to make full use of the limited caching space in routers,it is an urgent challenge to make an efficient cache replacement policy.However,the existing cache replacement policies only consider very few factors that affect the cache performance.In this paper,we present a cache replacement policy based on multi-factors for NDN(CRPM),in which the content with the least cache value is evicted from the caching space.CRPM fully analyzes multi-factors that affect the caching performance,puts forward the corresponding calculation methods,and utilize the multi-factors to measure the cache value of contents.Furthermore,a new cache value function is constructed,which makes the content with high value be stored in the router as long as possible,so as to ensure the efficient use of cache resources.The simulation results show that CPRM can effectively improve cache hit ratio,enhance cache resource utilization,reduce energy consumption and decrease hit distance of content acquisition.展开更多
In order to extend the application scope of NDN and realize the transmission of different NDNs across IP networks,a method for interconnecting NDN networks distributed in different areas with IP networks is proposed.F...In order to extend the application scope of NDN and realize the transmission of different NDNs across IP networks,a method for interconnecting NDN networks distributed in different areas with IP networks is proposed.Firstly,the NDN data resource is located by means of the DNS mechanism,and the gateway IP address of the NDN network where the data resource is located is found.Then,the transmission between different NDNs across the IP network is implemented based on the tunnel technology.In addition,in order to achieve efficient and fast NDN data forwarding,we have added a small number of NDN service nodes in the IP network,and proposed an adaptive probabilistic forwarding strategy and a link cost function-based forwarding strategy to make NDN data obtaining the cache service provided by the NDN service node as much as possible.The results of analysis and simulation experiments show that,the interconnectionmethod of NDN across IP network proposed is generally effective and feasible,and the link cost function forwarding strategy is better than the adaptive probability forwarding strategy.展开更多
无人机和无人船组成的移动自组织网络存在通信环境恶劣和网络拓扑结构变化频繁等挑战,导致网络性能变差。针对这一问题,建立以数据为中心的命名数据网络(Named Data Networking, NDN)网络架构,在此基础上提出基于深度强化学习的智能数...无人机和无人船组成的移动自组织网络存在通信环境恶劣和网络拓扑结构变化频繁等挑战,导致网络性能变差。针对这一问题,建立以数据为中心的命名数据网络(Named Data Networking, NDN)网络架构,在此基础上提出基于深度强化学习的智能数据转发策略。利用深度强化学习实时感知网络动态变化,优化数据转发策略,设计优先采样和双重Q网络算法,加快深度强化学习收敛速度。实验结果表明,该策略可以有效降低时延并提高兴趣包满足率。展开更多
As a named data-based clean-slate future Internet architecture,Content-Centric Networking(CCN)uses entirely different protocols and communication patterns from the host-to-host IP network.In CCN,communication is wholl...As a named data-based clean-slate future Internet architecture,Content-Centric Networking(CCN)uses entirely different protocols and communication patterns from the host-to-host IP network.In CCN,communication is wholly driven by the data consumer.Consumers must send Interest packets with the content name and not by the host’s network address.Its nature of in-network caching,Interest packets aggregation and hop-byhop communication poses unique challenges to provision of Internet applications,where traditional IP network no long works well.This paper presents a comprehensive survey of state-of-the-art application research activities related to CCN architecture.Our main aims in this survey are(a)to identify the advantages and drawbacks of CCN architectures for application provisioning;(b)to discuss the challenges and opportunities regarding service provisioning in CCN architectures;and(c)to further encourage deeper thinking about design principles for future Internet architectures from the perspective of upper-layer applications.展开更多
针对命名数据网络(named data networking,NDN)路径选择过程中传输速度慢的问题,采用蝙蝠算法优化NDN网络的路径选择。为了证明蝙蝠算法在路径选择上的优势,将蝙蝠算法、遗传算法和粒子群算法进行对比,得出蝙蝠算法求得最优解的概率更...针对命名数据网络(named data networking,NDN)路径选择过程中传输速度慢的问题,采用蝙蝠算法优化NDN网络的路径选择。为了证明蝙蝠算法在路径选择上的优势,将蝙蝠算法、遗传算法和粒子群算法进行对比,得出蝙蝠算法求得最优解的概率更高、收敛速度更快,为此提出了一种基于蝙蝠算法的NDN网络路径选择(bat algorithm-path selection in NDN,BA-PSNDN)方法。对传输过程中的节点进行实时更新并计算,通过迭代选出最优路径进行数据传输。使用ndnSIM2.7软件进行仿真,通过在兴趣包和数据包中加入自定义段,保存数据包传输过程中的信息并进行路径选择,仿真出最优路径后输出时延信息。结果表明,BA-PSNDN方法在减少网络传输时延方面更优。展开更多
在命名数据网络(named data networking,NDN)中,拥塞控制是保障用户服务质量(quality of service,QoS)的关键环节.但独特的多源、多路径特性使得TCP/IP架构的端到端拥塞控制方案难以直接应用于NDN.因此,设计一种有效的NDN拥塞控制机制...在命名数据网络(named data networking,NDN)中,拥塞控制是保障用户服务质量(quality of service,QoS)的关键环节.但独特的多源、多路径特性使得TCP/IP架构的端到端拥塞控制方案难以直接应用于NDN.因此,设计一种有效的NDN拥塞控制机制是较为活跃的研究领域.目前,混合拥塞控制逐渐发展成为一种主流的拥塞控制机制;然而,如何及时有效地既能缓解由单路径流引发的拥塞又能缓解由多路径流引发的网络拥塞是混合拥塞控制机制亟待解决的问题.针对该问题,提出了一种基于转发路径数目的混合拥塞控制方案——NFPCC.路由器依据数据包排队时延计算本地节点的拥塞程度,并使用数据包传递当前节点的拥塞信息;下游邻节点提取数据包中的拥塞信息并依据兴趣包的转发路径数量选择多路径转发策略或兴趣包速率整形策略以及时、有效地缓解上游相邻节点的拥塞;最后,消费者依据数据包所传递的拥塞信息持续地地调整拥塞窗口cwnd的尺寸以协作路由器的控制.仿真结果表明,在BRITE场景中,基于所提方案的消费者总吞吐量比基于PCON方案的消费者总吞吐量高91.9%.在路由器启用网络内缓存功能后,基于所提方案的消费者总吞吐量比基于PCON方案的消费者总吞吐量高38.5%.展开更多
Inheriting from a data-driven communication pattern other than a location-driven pattern, named data net- working (NDN) offers better support to network-layer dataflow. However, the application developers have to ha...Inheriting from a data-driven communication pattern other than a location-driven pattern, named data net- working (NDN) offers better support to network-layer dataflow. However, the application developers have to handle complex tasks, such as data segmentation, packet verification, and flow control, due to the lack of proper transport-layer protocols over the network layer. In this study, we design a dataflow-oriented programming interface to provide transport strategies for NDN, which greatly improves the efficiency in developing applications. This interface presents two application data unit; (ADU) retrieval strategies according to different data publishing patterns, in which it adopts an adaptive ADU pipelining algorithm to control the dataflow based on the current network status and data generation rate. The interface also offers network measurement strategies to monitor an abundance of critical metrics infuencing the application performance. We verify the functionality and performance of our interface by implementing a video streaming application spanning 11 time zones over the worldwide NDN testbed. Our experiments show that the interface can efficiently support developing high-performance and dataflow-driven NDN applications.展开更多
Contents such as audios,videos,and images,contribute most of the Internet traffic in the current paradigm.Secure content sharing is a tedious issue.The existing security solutions do not secure data but secure the com...Contents such as audios,videos,and images,contribute most of the Internet traffic in the current paradigm.Secure content sharing is a tedious issue.The existing security solutions do not secure data but secure the communicating endpoints.Named data networking(NDN)secures the data by enforcing the data publisher to sign the data.Any user can verify the data by using the public key of the publisher.NDN is resilient to most of the probable security attacks in the TCP/IP model due to its new architecture.However,new types of attacks are possible in NDN.This article surveys the most significant security attacks in NDN such as interest flooding attacks,cache privacy attacks,cache pollution attacks,and content poisoning attacks.Each attack is classified according to their behavior and discussed for their detection techniques,countermeasures,and the affected parameters.The article is an attempt to help new researchers in this area to gather the domain knowledge of NDN.The article also provides open research issues that could be addressed by researchers.展开更多
针对当前基于Trie的变长层次化且可以无限长度的命名的数据网络(Named Data Networking,NDN)内容名称的最长前缀匹配查找策略存在复杂性高、查找速率低且树型数据结构的更新开销高等问题,导致算法效率低,提出一种快速的贪婪名称查找机制...针对当前基于Trie的变长层次化且可以无限长度的命名的数据网络(Named Data Networking,NDN)内容名称的最长前缀匹配查找策略存在复杂性高、查找速率低且树型数据结构的更新开销高等问题,导致算法效率低,提出一种快速的贪婪名称查找机制(FGNL)来实现数据包的快速转发。快速的贪婪的组件代码分配机制复杂性较低,容易实现,支持快速更新;组件编码树本质上是一个二维状态转移表,进一步转换成快速的哈希表查找;多哈希表结构创建速度快,且压缩存储空间,能够极大地加快名称查找的速度。实验结果证明,与字符查找树相比FGNL方案减少大约48.71%的内存,与NCE相比节省26.98%的存储空间,且查找速度获得了2倍的加速。评估结果也表明,该方案可以向上扩展来适应名称集潜在的未来增长。展开更多
命名数据网络(named data networking,NDN)中,命名链路状态路由协议(named-data link state routing protocol,NLSR)并非针对移动场景所设计,特别是对移动设备作为内容源的支持上存在FIB更新严重滞后、请求响应延时过大、内容响应率过...命名数据网络(named data networking,NDN)中,命名链路状态路由协议(named-data link state routing protocol,NLSR)并非针对移动场景所设计,特别是对移动设备作为内容源的支持上存在FIB更新严重滞后、请求响应延时过大、内容响应率过低等问题。提出了一种针对内容源移动问题的NLSR优化方法(optimized NLSR for source mobility,NLSR-SM)。该方法采用内容源提前报告移动信息,网络中转节点提前更新FIB的策略,实现对内容源移动性的更好支持。通过在ndn SIM上实现NLSR-SM的原型系统,在不同实验场景下对NLSR-SM进行实验并与NLSR进行对比。实验结果表明,NLSR-SM可以降低请求响应的往返延时,提高内容响应率。对于移动直播的场景,NLSR-SM能够提高单次请求的内容响应率。NLSR-SM机制可以有效应对内容源在NDN中移动服务的问题。展开更多
随着网络传输带宽以及用户对实时应用需求的增加,如何在充分利用瓶颈带宽的同时降低缓存占用率以及传输时延,成为传输控制的一个新问题。提出了一种基于瓶颈带宽以及往返时延(round-trip time,RTT)的命名数据网络(named data networking...随着网络传输带宽以及用户对实时应用需求的增加,如何在充分利用瓶颈带宽的同时降低缓存占用率以及传输时延,成为传输控制的一个新问题。提出了一种基于瓶颈带宽以及往返时延(round-trip time,RTT)的命名数据网络(named data networking,NDN)拥塞控制算法。该算法不使用传统的基于丢包的拥塞感知与调节方法,而是主动控制注入网络的流量,使其匹配链路的传输能力。通过在接收端对一定时间范围内反馈的即时带宽和往返时延进行统计,估计传输链路的瓶颈带宽以及物理链路延迟的值,配合由状态决定的增益来控制Interest包的发送速率以及窗口的大小。在ndnSIM模拟器中实现了该算法,并与ICP(interest control protocol)拥塞控制算法进行对比,证明了在充分利用瓶颈带宽的同时,该算法能够实现更低的传输时延以及更快的收敛速度。展开更多
命名数据网络(named data networking,NDN)中的请求-应答通信模式及有状态的转发滋生了新的分布式拒绝服务(distributed denial of service,DDoS)攻击方式-兴趣洪泛攻击(interest flooding attack,IFA)。IFA是NDN中主要的拒绝服务威胁,...命名数据网络(named data networking,NDN)中的请求-应答通信模式及有状态的转发滋生了新的分布式拒绝服务(distributed denial of service,DDoS)攻击方式-兴趣洪泛攻击(interest flooding attack,IFA)。IFA是NDN中主要的拒绝服务威胁,虽然IFA防御方案被广泛研究,但目前缺乏系统的解决方案。针对这一问题,基于粒子群优化的后向传播神经网络算法提出一种新的IFA检测方法,并结合基于基尼不纯度的恶意前缀识别方法和兴趣包回溯方法来缓解攻击危害,形成一种综合的防御方案。通过ndnSIM仿真实验证明,提出的方案不仅可以准确检测和有效防御IFA攻击,而且解决了基于窗口检测方案无法检测连续攻击的问题。展开更多
为提高命名数据网络(Name Data Networking,NDN)路由过程中内容名字查找的效率,该文提出一种基于深度布隆过滤器的3级名字查找方法。该方法使用长短记忆神经网络(Long Short Term Memory,LSTM)与标准布隆过滤器相结合的方法优化名字查...为提高命名数据网络(Name Data Networking,NDN)路由过程中内容名字查找的效率,该文提出一种基于深度布隆过滤器的3级名字查找方法。该方法使用长短记忆神经网络(Long Short Term Memory,LSTM)与标准布隆过滤器相结合的方法优化名字查找过程;采用3级结构优化内容名字在内容存储器(Content Store,CS)、待定请求表(Pending Interest Table,PIT)中的精确查找过程,提高查找精度并降低内存消耗。从理论上分析了3级名字查找方法的假阳性率,并通过实验验证了该方法能够有效节省内存、降低查找过程的假阳性。展开更多
基金This research was funded by the National Natural Science Foundation of China(No.61862046)the Inner Mongolia Natural Science Foundation of China under Grant No.2018MS06024+2 种基金the Research Project of Higher Education School of Inner Mongolia Autonomous Region under Grant NJZY18010the Inner Mongolia Autonomous Region Science and Technology Achievements Transformation Project(No.CGZH2018124)the CERNET Innovation Project under Grant No.NGII20180626.
文摘Named Data Networking(NDN)is one of the most excellent future Internet architectures and every router in NDN has the capacity of caching contents passing by.It greatly reduces network traffic and improves the speed of content distribution and retrieval.In order to make full use of the limited caching space in routers,it is an urgent challenge to make an efficient cache replacement policy.However,the existing cache replacement policies only consider very few factors that affect the cache performance.In this paper,we present a cache replacement policy based on multi-factors for NDN(CRPM),in which the content with the least cache value is evicted from the caching space.CRPM fully analyzes multi-factors that affect the caching performance,puts forward the corresponding calculation methods,and utilize the multi-factors to measure the cache value of contents.Furthermore,a new cache value function is constructed,which makes the content with high value be stored in the router as long as possible,so as to ensure the efficient use of cache resources.The simulation results show that CPRM can effectively improve cache hit ratio,enhance cache resource utilization,reduce energy consumption and decrease hit distance of content acquisition.
基金supported by Beijing Advanced Innovation Center for Materials Genome Engineering,Beijing Information Science and Technology University。
文摘In order to extend the application scope of NDN and realize the transmission of different NDNs across IP networks,a method for interconnecting NDN networks distributed in different areas with IP networks is proposed.Firstly,the NDN data resource is located by means of the DNS mechanism,and the gateway IP address of the NDN network where the data resource is located is found.Then,the transmission between different NDNs across the IP network is implemented based on the tunnel technology.In addition,in order to achieve efficient and fast NDN data forwarding,we have added a small number of NDN service nodes in the IP network,and proposed an adaptive probabilistic forwarding strategy and a link cost function-based forwarding strategy to make NDN data obtaining the cache service provided by the NDN service node as much as possible.The results of analysis and simulation experiments show that,the interconnectionmethod of NDN across IP network proposed is generally effective and feasible,and the link cost function forwarding strategy is better than the adaptive probability forwarding strategy.
文摘无人机和无人船组成的移动自组织网络存在通信环境恶劣和网络拓扑结构变化频繁等挑战,导致网络性能变差。针对这一问题,建立以数据为中心的命名数据网络(Named Data Networking, NDN)网络架构,在此基础上提出基于深度强化学习的智能数据转发策略。利用深度强化学习实时感知网络动态变化,优化数据转发策略,设计优先采样和双重Q网络算法,加快深度强化学习收敛速度。实验结果表明,该策略可以有效降低时延并提高兴趣包满足率。
基金supported in part by the National Natural Science Foundation of China (NSFC) under Grant 61671081in part by the Funds for International Cooperation and Exchange of NSFC under Grant 61720106007+2 种基金in part by the 111 Project under Grant B18008in part by the Beijing Natural Science Foundation under Grant 4172042in part by the Fundamental Research Funds for the Central Universities under Grant 2018XKJC01
文摘As a named data-based clean-slate future Internet architecture,Content-Centric Networking(CCN)uses entirely different protocols and communication patterns from the host-to-host IP network.In CCN,communication is wholly driven by the data consumer.Consumers must send Interest packets with the content name and not by the host’s network address.Its nature of in-network caching,Interest packets aggregation and hop-byhop communication poses unique challenges to provision of Internet applications,where traditional IP network no long works well.This paper presents a comprehensive survey of state-of-the-art application research activities related to CCN architecture.Our main aims in this survey are(a)to identify the advantages and drawbacks of CCN architectures for application provisioning;(b)to discuss the challenges and opportunities regarding service provisioning in CCN architectures;and(c)to further encourage deeper thinking about design principles for future Internet architectures from the perspective of upper-layer applications.
文摘针对命名数据网络(named data networking,NDN)路径选择过程中传输速度慢的问题,采用蝙蝠算法优化NDN网络的路径选择。为了证明蝙蝠算法在路径选择上的优势,将蝙蝠算法、遗传算法和粒子群算法进行对比,得出蝙蝠算法求得最优解的概率更高、收敛速度更快,为此提出了一种基于蝙蝠算法的NDN网络路径选择(bat algorithm-path selection in NDN,BA-PSNDN)方法。对传输过程中的节点进行实时更新并计算,通过迭代选出最优路径进行数据传输。使用ndnSIM2.7软件进行仿真,通过在兴趣包和数据包中加入自定义段,保存数据包传输过程中的信息并进行路径选择,仿真出最优路径后输出时延信息。结果表明,BA-PSNDN方法在减少网络传输时延方面更优。
文摘在命名数据网络(named data networking,NDN)中,拥塞控制是保障用户服务质量(quality of service,QoS)的关键环节.但独特的多源、多路径特性使得TCP/IP架构的端到端拥塞控制方案难以直接应用于NDN.因此,设计一种有效的NDN拥塞控制机制是较为活跃的研究领域.目前,混合拥塞控制逐渐发展成为一种主流的拥塞控制机制;然而,如何及时有效地既能缓解由单路径流引发的拥塞又能缓解由多路径流引发的网络拥塞是混合拥塞控制机制亟待解决的问题.针对该问题,提出了一种基于转发路径数目的混合拥塞控制方案——NFPCC.路由器依据数据包排队时延计算本地节点的拥塞程度,并使用数据包传递当前节点的拥塞信息;下游邻节点提取数据包中的拥塞信息并依据兴趣包的转发路径数量选择多路径转发策略或兴趣包速率整形策略以及时、有效地缓解上游相邻节点的拥塞;最后,消费者依据数据包所传递的拥塞信息持续地地调整拥塞窗口cwnd的尺寸以协作路由器的控制.仿真结果表明,在BRITE场景中,基于所提方案的消费者总吞吐量比基于PCON方案的消费者总吞吐量高91.9%.在路由器启用网络内缓存功能后,基于所提方案的消费者总吞吐量比基于PCON方案的消费者总吞吐量高38.5%.
基金This work is supported by the National Natural Science Foundation of China under Grant No. 61373025.
文摘Inheriting from a data-driven communication pattern other than a location-driven pattern, named data net- working (NDN) offers better support to network-layer dataflow. However, the application developers have to handle complex tasks, such as data segmentation, packet verification, and flow control, due to the lack of proper transport-layer protocols over the network layer. In this study, we design a dataflow-oriented programming interface to provide transport strategies for NDN, which greatly improves the efficiency in developing applications. This interface presents two application data unit; (ADU) retrieval strategies according to different data publishing patterns, in which it adopts an adaptive ADU pipelining algorithm to control the dataflow based on the current network status and data generation rate. The interface also offers network measurement strategies to monitor an abundance of critical metrics infuencing the application performance. We verify the functionality and performance of our interface by implementing a video streaming application spanning 11 time zones over the worldwide NDN testbed. Our experiments show that the interface can efficiently support developing high-performance and dataflow-driven NDN applications.
文摘Contents such as audios,videos,and images,contribute most of the Internet traffic in the current paradigm.Secure content sharing is a tedious issue.The existing security solutions do not secure data but secure the communicating endpoints.Named data networking(NDN)secures the data by enforcing the data publisher to sign the data.Any user can verify the data by using the public key of the publisher.NDN is resilient to most of the probable security attacks in the TCP/IP model due to its new architecture.However,new types of attacks are possible in NDN.This article surveys the most significant security attacks in NDN such as interest flooding attacks,cache privacy attacks,cache pollution attacks,and content poisoning attacks.Each attack is classified according to their behavior and discussed for their detection techniques,countermeasures,and the affected parameters.The article is an attempt to help new researchers in this area to gather the domain knowledge of NDN.The article also provides open research issues that could be addressed by researchers.
文摘针对当前基于Trie的变长层次化且可以无限长度的命名的数据网络(Named Data Networking,NDN)内容名称的最长前缀匹配查找策略存在复杂性高、查找速率低且树型数据结构的更新开销高等问题,导致算法效率低,提出一种快速的贪婪名称查找机制(FGNL)来实现数据包的快速转发。快速的贪婪的组件代码分配机制复杂性较低,容易实现,支持快速更新;组件编码树本质上是一个二维状态转移表,进一步转换成快速的哈希表查找;多哈希表结构创建速度快,且压缩存储空间,能够极大地加快名称查找的速度。实验结果证明,与字符查找树相比FGNL方案减少大约48.71%的内存,与NCE相比节省26.98%的存储空间,且查找速度获得了2倍的加速。评估结果也表明,该方案可以向上扩展来适应名称集潜在的未来增长。
文摘命名数据网络(named data networking,NDN)中,命名链路状态路由协议(named-data link state routing protocol,NLSR)并非针对移动场景所设计,特别是对移动设备作为内容源的支持上存在FIB更新严重滞后、请求响应延时过大、内容响应率过低等问题。提出了一种针对内容源移动问题的NLSR优化方法(optimized NLSR for source mobility,NLSR-SM)。该方法采用内容源提前报告移动信息,网络中转节点提前更新FIB的策略,实现对内容源移动性的更好支持。通过在ndn SIM上实现NLSR-SM的原型系统,在不同实验场景下对NLSR-SM进行实验并与NLSR进行对比。实验结果表明,NLSR-SM可以降低请求响应的往返延时,提高内容响应率。对于移动直播的场景,NLSR-SM能够提高单次请求的内容响应率。NLSR-SM机制可以有效应对内容源在NDN中移动服务的问题。
文摘随着网络传输带宽以及用户对实时应用需求的增加,如何在充分利用瓶颈带宽的同时降低缓存占用率以及传输时延,成为传输控制的一个新问题。提出了一种基于瓶颈带宽以及往返时延(round-trip time,RTT)的命名数据网络(named data networking,NDN)拥塞控制算法。该算法不使用传统的基于丢包的拥塞感知与调节方法,而是主动控制注入网络的流量,使其匹配链路的传输能力。通过在接收端对一定时间范围内反馈的即时带宽和往返时延进行统计,估计传输链路的瓶颈带宽以及物理链路延迟的值,配合由状态决定的增益来控制Interest包的发送速率以及窗口的大小。在ndnSIM模拟器中实现了该算法,并与ICP(interest control protocol)拥塞控制算法进行对比,证明了在充分利用瓶颈带宽的同时,该算法能够实现更低的传输时延以及更快的收敛速度。
文摘命名数据网络(named data networking,NDN)中的请求-应答通信模式及有状态的转发滋生了新的分布式拒绝服务(distributed denial of service,DDoS)攻击方式-兴趣洪泛攻击(interest flooding attack,IFA)。IFA是NDN中主要的拒绝服务威胁,虽然IFA防御方案被广泛研究,但目前缺乏系统的解决方案。针对这一问题,基于粒子群优化的后向传播神经网络算法提出一种新的IFA检测方法,并结合基于基尼不纯度的恶意前缀识别方法和兴趣包回溯方法来缓解攻击危害,形成一种综合的防御方案。通过ndnSIM仿真实验证明,提出的方案不仅可以准确检测和有效防御IFA攻击,而且解决了基于窗口检测方案无法检测连续攻击的问题。
文摘为提高命名数据网络(Name Data Networking,NDN)路由过程中内容名字查找的效率,该文提出一种基于深度布隆过滤器的3级名字查找方法。该方法使用长短记忆神经网络(Long Short Term Memory,LSTM)与标准布隆过滤器相结合的方法优化名字查找过程;采用3级结构优化内容名字在内容存储器(Content Store,CS)、待定请求表(Pending Interest Table,PIT)中的精确查找过程,提高查找精度并降低内存消耗。从理论上分析了3级名字查找方法的假阳性率,并通过实验验证了该方法能够有效节省内存、降低查找过程的假阳性。