专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120047096A1 METHOD AND APPARATUS FOR CLASSIFYING APPLICATIONS USING THE COLLECTIVE PROPERTIES OF NETWORK TRAFFIC 有权
标题翻译：使用网络交通的集合性质分类应用的方法和装置
公开(公告)号：US20120047096A1
公开(公告)日：2012-02-23
申请号：US12858303
申请日：2010-08-17
申请人： Nicholas Duffield , Patrick Haffner , Yu Jin , Subhabrata Sen , Zhi-Li Zhang
发明人： Nicholas Duffield , Patrick Haffner , Yu Jin , Subhabrata Sen , Zhi-Li Zhang
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： H04L43/045 , H04L43/026 , H04L67/22
摘要： In one embodiment, the present disclosure is a method and apparatus for classifying applications using the collective properties of network traffic. In one embodiment, a method for classifying traffic in a communication network includes receiving a traffic activity graph, the traffic activity graph comprising a plurality of nodes interconnected by a plurality of edges, where each of the nodes represents an endpoint associated with the communication network and each of the edges represents traffic between a corresponding pair of the nodes, generating an initial set of inferences as to an application class associated with each of the edges, based on at least one measured statistic related to at least one traffic flow in the communication network, and refining the initial set of inferences based on a spatial distribution of the traffic flows, to produce a final traffic activity graph.
摘要翻译：在一个实施例中，本公开是用于使用网络业务的集合属性对应用进行分类的方法和装置。在一个实施例中，用于对通信网络中的业务进行分类的方法包括接收业务活动图，所述业务活动图包括由多个边缘互连的多个节点，其中每个节点表示与所述通信网络相关联的端点，每个边缘表示对应的一对节点之间的流量，基于与通信网络中的至少一个业务流相关的至少一个测量的统计量，生成关于与每个边缘相关联的应用类别的初始推断集合，并且基于业务流的空间分布来优化初始推理集合，以产生最终业务活动图。

2. 发明授权

US08935188B2 Method and apparatus for classifying applications using the collective properties of network traffic in a traffic activity graph 有权
标题翻译：使用交通活动图中网络流量的集体属性对应用进行分类的方法和装置
公开(公告)号：US08935188B2
公开(公告)日：2015-01-13
申请号：US12858303
申请日：2010-08-17
申请人： Nicholas Duffield , Patrick Haffner , Yu Jin , Subhabrata Sen , Zhi-Li Zhang
发明人： Nicholas Duffield , Patrick Haffner , Yu Jin , Subhabrata Sen , Zhi-Li Zhang
IPC分类号： G06F15/18 , G06F15/173 , H04L12/26 , H04L29/08
CPC分类号： H04L43/045 , H04L43/026 , H04L67/22
摘要： In one embodiment, the present disclosure is a method and apparatus for classifying applications using the collective properties of network traffic. In one embodiment, a method for classifying traffic in a communication network includes receiving a traffic activity graph, the traffic activity graph comprising a plurality of nodes interconnected by a plurality of edges, where each of the nodes represents an endpoint associated with the communication network and each of the edges represents traffic between a corresponding pair of the nodes, generating an initial set of inferences as to an application class associated with each of the edges, based on at least one measured statistic related to at least one traffic flow in the communication network, and refining the initial set of inferences based on a spatial distribution of the traffic flows, to produce a final traffic activity graph.
摘要翻译：在一个实施例中，本公开是用于使用网络业务的集合属性对应用进行分类的方法和装置。在一个实施例中，用于对通信网络中的业务进行分类的方法包括接收业务活动图，所述业务活动图包括由多个边缘互连的多个节点，其中每个节点表示与所述通信网络相关联的端点，每个边缘表示对应的一对节点之间的流量，基于与通信网络中的至少一个业务流相关的至少一个测量的统计量，生成关于与每个边缘相关联的应用类别的初始推断集合，并且基于业务流的空间分布来优化初始推理集合，以产生最终业务活动图。

3. 发明授权

US08311956B2 Scalable traffic classifier and classifier training system 有权
标题翻译：可扩展流量分类器和分类器训练系统
公开(公告)号：US08311956B2
公开(公告)日：2012-11-13
申请号：US12539430
申请日：2009-08-11
申请人： Subhabrata Sen , Nicholas Duffield , Patrick Haffner , Jeffrey Erman , Yu Jin
发明人： Subhabrata Sen , Nicholas Duffield , Patrick Haffner , Jeffrey Erman , Yu Jin
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.
摘要翻译：流量分类器具有多个二进制分类器，每个二进制分类器与多个校准器之一相关联。每个校准器被训练成使用拟合的逻辑曲线将相关联的二进制分类器的输出得分转换成估计的类概率值，每个估计的类概率值指示输出得分所基于的分组流的概率属于相关联的流量类别与校准器相关联的二进制分类器。分类器训练系统被配置为基于使用流和分组采样方法获得的网络信息生成训练数据。在一些实施例中，分类器训练系统被配置为生成减少的训练数据集，每个业务类别一个，减少与业务类别不相关的业务相关的训练数据。

4. 发明授权

US09349102B2 Scalable traffic classifier and classifier training system 有权
标题翻译：可扩展流量分类器和分类器训练系统
公开(公告)号：US09349102B2
公开(公告)日：2016-05-24
申请号：US13620668
申请日：2012-09-14
申请人： Subhabrata Sen , Nicholas Duffield , Patrick Haffner , Jeffrey Erman , Yu Jin
发明人： Subhabrata Sen , Nicholas Duffield , Patrick Haffner , Jeffrey Erman , Yu Jin
IPC分类号： G06N99/00
CPC分类号： G06N99/005
摘要： A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.
摘要翻译：流量分类器具有多个二进制分类器，每个二进制分类器与多个校准器之一相关联。每个校准器被训练成使用拟合的逻辑曲线将相关联的二进制分类器的输出得分转换成估计的类概率值，每个估计的类概率值指示输出得分所基于的分组流的概率属于相关联的流量类别与校准器相关联的二进制分类器。分类器训练系统被配置为基于使用流和分组采样方法获得的网络信息生成训练数据。在一些实施例中，分类器训练系统被配置为生成减少的训练数据集，每个业务类别一个，减少与业务类别不相关的业务相关的训练数据。

5. 发明申请

US20110040706A1 SCALABLE TRAFFIC CLASSIFIER AND CLASSIFIER TRAINING SYSTEM 有权
标题翻译：可扩展的交通分类器和分类器培训系统
公开(公告)号：US20110040706A1
公开(公告)日：2011-02-17
申请号：US12539430
申请日：2009-08-11
申请人： Subhabrata Sen , Nicholas Duffield , Patrick Haffner , Jeffrey Erman , Yu Jin
发明人： Subhabrata Sen , Nicholas Duffield , Patrick Haffner , Jeffrey Erman , Yu Jin
IPC分类号： G06F15/18 , G06N5/02
CPC分类号： G06N99/005
摘要： A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.
摘要翻译：流量分类器具有多个二进制分类器，每个二进制分类器与多个校准器之一相关联。每个校准器被训练成使用拟合的逻辑曲线将相关联的二进制分类器的输出得分转换成估计的类概率值，每个估计的类概率值指示输出得分所基于的分组流的概率属于相关联的流量类别与校准器相关联的二进制分类器。分类器训练系统被配置为基于使用流和分组采样方法获得的网络信息生成训练数据。在一些实施例中，分类器训练系统被配置为生成减少的训练数据集，每个业务类别一个，减少与业务类别不相关的业务相关的训练数据。

6. 发明申请

US20090016234A1 METHODS AND APPARATUS FOR DETECTION OF HIERARCHICAL HEAVY HITTERS 有权
标题翻译：用于检测分层重型HITTERS的方法和装置
公开(公告)号：US20090016234A1
公开(公告)日：2009-01-15
申请号：US12236369
申请日：2008-09-23
申请人： Nicholas Duffield , Carsten Lund , Subhabrata Sen , Yin Zhang , Sumeet Singh
发明人： Nicholas Duffield , Carsten Lund , Subhabrata Sen , Yin Zhang , Sumeet Singh
IPC分类号： G06F11/30
CPC分类号： H04L63/1425 , H04L29/12801 , H04L61/6004 , H04L63/1441 , H04L63/1458 , Y10S707/99945 , Y10S707/99948
摘要： An efficient streaming method and apparatus for detecting hierarchical heavy hitters from massive data streams is disclosed. In one embodiment, the method enables near real time detection of anomaly behavior in networks.
摘要翻译：公开了一种用于从海量数据流检测分层重击打者的有效的流传输方法和装置。在一个实施例中，该方法能够近似实时地检测网络中的异常行为。

7. 发明申请

US20110013525A1 Indirect measurement methodology to infer routing changes using statistics of flow arrival processes 有权
标题翻译：使用统计流量到达过程来推断路由更改的间接测量方法
公开(公告)号：US20110013525A1
公开(公告)日：2011-01-20
申请号：US12460113
申请日：2009-07-14
申请人： Lee Breslau , Amogh Dhamdhere , Nicholas Duffield , Cheng Ee , Alexandre Gerber , Carsten Lund , Subhabrata Sen
发明人： Lee Breslau , Amogh Dhamdhere , Nicholas Duffield , Cheng Ee , Alexandre Gerber , Carsten Lund , Subhabrata Sen
IPC分类号： H04L12/26 , H04L12/56
CPC分类号： H04L43/18 , H04L43/062 , H04L45/70
摘要： Statistical methods are used to observe packet flow arrival processes and to infer routing changes from those observations. Packet flow arrivals are monitored using NetFlow or another packet flow monitoring arrangement. Packet flow arrivals are quantified by counting arrivals per unit time, or by measuring an inter-arrival time between flows. When a change in packet flow arrivals is determined to be statistically significant, a change in network routing protocol is reported.
摘要翻译：统计方法用于观察分组流到达过程，并从这些观察中推断出路由变化。使用NetFlow或另一个分组流监视装置来监视分组流到达。通过对每单位时间的到达时间进行计数，或通过测量流之间的到达之间的时间来量化分组流到达。当分组流到达的变化被确定为具有统计学意义时，报告了网络路由协议的变化。

8. 发明授权

US07437385B1 Methods and apparatus for detection of hierarchical heavy hitters 有权
标题翻译：用于检测分级重击锤的方法和装置
公开(公告)号：US07437385B1
公开(公告)日：2008-10-14
申请号：US11042771
申请日：2005-01-24
申请人： Nicholas Duffield , Carsten Lund , Subhabrata Sen , Yin Zhang , Sumeet Singh
发明人： Nicholas Duffield , Carsten Lund , Subhabrata Sen , Yin Zhang , Sumeet Singh
IPC分类号： G06F17/00 , G06F7/00
CPC分类号： H04L63/1425 , H04L29/12801 , H04L61/6004 , H04L63/1441 , H04L63/1458 , Y10S707/99945 , Y10S707/99948
摘要： An efficient streaming method and apparatus for detecting hierarchical heavy hitters from massive data streams is disclosed. In one embodiment, the method enables near real time detection of anomaly behavior in networks.
摘要翻译：公开了一种用于从海量数据流检测分层重击打者的有效的流传输方法和装置。在一个实施例中，该方法能够近似实时地检测网络中的异常行为。

9. 发明授权

US08477772B2 System and method for determination of routing information in a network 有权
标题翻译：用于确定网络中路由信息的系统和方法
公开(公告)号：US08477772B2
公开(公告)日：2013-07-02
申请号：US12335868
申请日：2008-12-16
申请人： Alexandre Gerber , Lee Breslau , Subhabrata Sen , Nicholas Duffield , Carsten Lund , Cheng Ee , Amogh Dhamdhere
发明人： Alexandre Gerber , Lee Breslau , Subhabrata Sen , Nicholas Duffield , Carsten Lund , Cheng Ee , Amogh Dhamdhere
IPC分类号： H04L12/56
CPC分类号： H04L12/56 , H04L41/12 , H04L45/70
摘要： A system and method to use network flow records to generate information about changes in network routing and to understand the impact of these changes on network traffic. The inferences made can be determinative, if sufficient information is available. If sufficient information is not available to make determinative inferences, inferences may be made that narrow the range of possible changes that may have occurred to network traffic and the underlying network.
摘要翻译：一种使用网络流记录生成有关网络路由更改的信息并了解这些更改对网络流量的影响的系统和方法。如果有足够的信息可用，所做的推论可以是决定性的。如果没有足够的信息可用于作出决定性推论，可以推测可能缩小网络流量和底层网络可能发生的可能变化的范围。

10. 发明授权

US07957315B2 System and method for sampling network traffic 有权
标题翻译：系统和方法对网络流量进行采样
公开(公告)号：US07957315B2
公开(公告)日：2011-06-07
申请号：US12342957
申请日：2008-12-23
申请人： Nicholas Duffield , Lee M. Breslau , Cheng Ee , Alexandre Gerber , Carsten Lund , Subhabrata Sen
发明人： Nicholas Duffield , Lee M. Breslau , Cheng Ee , Alexandre Gerber , Carsten Lund , Subhabrata Sen
IPC分类号： H04L12/26
CPC分类号： H04L43/04 , H04L43/022 , H04L43/026 , H04L43/062
摘要： Disclosed herein are systems, computer-implemented methods, and computer-readable media for sampling network traffic. The method includes receiving a plurality of flow records, calculating a hash for each flow record based on one or more invariant part of a respective flow, generating a quasi-random number from the calculated hash for each respective flow record, and sampling flow records having a quasi-random number below a probability P. Invariant parts of flow records include destination IP address, source IP address, TCP/UDP port numbers, TCP flags, and network protocol. A plurality of routers can uniformly calculate hashes for flow records. Each router in a plurality of routers can generate a same quasi-random number for each respective flow record and uses different values for probability P. The probability P can depend on a flow size. The method can divide the quasi-random number by a maximum possible hash value.
摘要翻译：本文公开了系统，计算机实现的方法和用于对网络业务进行采样的计算机可读介质。该方法包括：接收多个流记录，基于相应流的一个或多个不变部分计算每个流记录的散列，从针对每个相应流记录的计算出的散列生成准随机数，以及对具有低于概率P的准随机数。流记录的不变部分包括目的地IP地址，源IP地址，TCP / UDP端口号，TCP标志和网络协议。多个路由器可以统一计算流记录的哈希值。多个路由器中的每个路由器可以为每个相应的流记录生成相同的准随机数，并对概率P使用不同的值。概率P可以取决于流量大小。该方法可以将准随机数除以最大可能的哈希值。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式