WO2011143817A1 - 应用协议识别方法及装置 - Google Patents
应用协议识别方法及装置 Download PDFInfo
- Publication number
- WO2011143817A1 WO2011143817A1 PCT/CN2010/072923 CN2010072923W WO2011143817A1 WO 2011143817 A1 WO2011143817 A1 WO 2011143817A1 CN 2010072923 W CN2010072923 W CN 2010072923W WO 2011143817 A1 WO2011143817 A1 WO 2011143817A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- keyword
- communication
- weight vector
- protocol
- application protocol
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/02—Capturing of monitoring data
- H04L43/028—Capturing of monitoring data by filtering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/02—Capturing of monitoring data
- H04L43/026—Capturing of monitoring data using flow identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
- H04L47/2475—Traffic characterised by specific attributes, e.g. priority or QoS for supporting traffic characterised by the type of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
- H04L63/0245—Filtering by information in the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/18—Protocol analysers
Definitions
- the present invention relates to network communication technologies, and more particularly to protocol identification techniques. Background technique
- the present invention proposes a method of identifying and classifying application layer protocol types in data received by an access gateway or other device in a data network such as a TCP/IP network.
- the application protocol identifies the type of protocol used to determine the data carried in the network. This is a very important technology for providing information characteristics of network traffic, which is essential in many different situations, such as effective network planning and design, security policies such as lawful monitoring and network shielding, such as traffic shaping. Quality of service and service differentiation, and pricing strategy design, etc.
- Most data networks use the TCP/IP reference model, which consists of five layers: physical layer, data link layer, network layer, transport layer, and application layer.
- Relay nodes such as access gateways typically only involve the transmission and relaying of the IP layer, but are not aware of the content carried by the upper layers (the transport layer and the application layer). However, in some cases, such as shielding a particular type of application, the relay node must find an efficient way to identify and determine the type of protocol carried by the application layer. Summary of the invention
- the usual application protocol identification scheme mainly includes the following three categories:
- Protocol classification by port number is the simplest and most traditional method.
- the method identifies the protocol or application type by the port number contained in the transport layer header.
- the relationship between the port number and the protocol is defined by the Internet Assigned Numbers Authority (IANA).
- IANA Internet Assigned Numbers Authority
- the HTTP protocol typically uses port 80 and the SMTP protocol uses port 25.
- the port number is usually defined by the protocol or the application itself. Because of the protocol and port This correspondence between numbers can be determined by the application layer protocol header, such as the source port field in the TCP header, and the port number of the destination port field.
- port number based protocol identification is efficient and easy to implement, it has several significant drawbacks. 1) In some protocols, the port number actually used is dynamically allocated during operation. 2) The widespread use of firewalls makes it easier for some ports to traverse the firewall than others; therefore, to ensure connectivity, whether it is used directly or encapsulated in the original protocol, the use of popular ports for proprietary protocols is on the rise. 3) - Some protocols explicitly use non-standard ports to avoid being identified, even some P2P applications allow users to change the default port, and some combinations of tunneling techniques and random port selection to avoid detection. Therefore, protocol identification based solely on port numbers is no longer reliable.
- the payload-based classification is the detection of the payload of the protocol carried in the communication packet by deep packet inspection (DPI) techniques.
- the method includes: finding a determined feature string in an application layer packet, for example, the string 'http/ ⁇ corresponds to an HTTP application, and the string '0xe319010000, corresponding to the eMule application.
- a single signature is not reliable enough to determine the protocol type, for example the string 'http/ ⁇ can also appear in the kazza protocol.
- Regular expressions provide a flexible, powerful representation that provides high-accuracy protocol identification.
- a finite automaton DFA
- fully compiling a regular expression into a DFA state that determines the number of exponents that can result in a finite automaton will degrade performance.
- Behavior-based protocol identification does not detect the content of the communication, but rather identifies the protocol based on the observed behavior or characteristics of the communication, such as the size of the packet, the number of connections, and the like.
- a common behavior-based protocol identification uses statistical features to identify and classify communications in terms of applications. For example, a document proposes the use of supervised machine learning to identify Internet traffic streams. The basic goal of classification is communication flow, which is expressed as one or more data packets between a given pair of hosts. Each communication stream has several descriptions of it The characteristics of the behavior (parameters). These parameters form the input discriminator for application identification. For example, a flow period, a packet arrival time, a payload size, a Fourier transform of a packet arrival time, and the like can be used as an input discriminator.
- Behavior-based protocol recognition results in less performance overhead than content-based protocol identification, it has multiple limitations.
- Behavior-based protocol identification is typically less accurate than content-based protocol identification. Since it relies mainly on statistical descriptions, its recognition accuracy is not stable relative to the payload-based determination method.
- the observed behavior always depends on the external environment, such as network type, host processing power. For example, the packet arrival interval in a wireless local area network (WLAN) may be different from Ethernet.
- WLAN wireless local area network
- the present invention proposes a method and apparatus for implementing application protocol identification based on keyword vector matching.
- a method of identifying an application protocol comprises the steps of: A. classifying a data packet to be detected into a separate communication stream; B. retrieving a keyword in a payload of the communication stream based on a keyword library of the identifiable application protocol, and determining the Keyword weight vector of the communication stream; wherein the weight of a keyword is related to its position in the payload of a communication stream; C. determining the key weight vector of the communication stream and the feature key of the identifiable application protocol a similarity between the weight vectors; D. if the predetermined condition is satisfied, determining an application protocol corresponding to the feature key weight vector having the highest similarity between the keyword weight vectors of the communication stream as the communication stream Application protocol.
- the method for identifying an application protocol further includes the steps before the step A: a. retrieving keywords in the payload of the plurality of training communication flows based on a keyword library of the identifiable application protocol And determining a key weight vector of the plurality of training communication flows; b. determining, according to the keyword weight vector of the plurality of training communication flows A feature key weight vector corresponding to each identifiable application protocol.
- a protocol identification device for identifying an application protocol.
- the protocol identification device includes: a first device, configured to classify a data packet to be detected into a separate communication flow; and a second device, configured to retrieve a payload of the communication flow based on a keyword library of an identifiable application protocol Keyword, and determining a keyword weight vector of the communication stream; wherein a weight of a keyword is related to its position in a payload of a communication stream; a third device, a keyword for determining the communication stream a similarity between the weight vector and the feature key weight vector of the identifiable application protocol; the fourth device, configured to: if the predetermined condition is met, have the highest similarity between the key weight vector of the communication stream The application protocol corresponding to the feature key weight vector is determined as an application protocol of the communication stream.
- a network device that includes the protocol identification device of the present invention described above.
- FIG. 1 is a flow chart showing a method of identifying an application protocol according to an embodiment of the present invention
- FIG. 2 is a flow chart showing determining a feature key weight vector in a method of identifying an application protocol according to an embodiment of the present invention
- FIG. 3 shows a block diagram of a protocol identifying apparatus according to an embodiment of the present invention. detailed description
- the keywords in the agreement For example, but not limited to, the keywords of the hypertext transfer protocol include "http/", and the keywords of the file transfer protocol include "ftp/", and the like.
- the received data packets are classified into separate communication flows according to the quintuple.
- the quintuple includes: source address, destination address, source port number, destination port number, and transport protocol type. For each individual communication stream, detecting a keyword in its payload can obtain a keyword weight vector, and matching the keyword weight vector with the characteristic key weight vector of the identifiable protocol can achieve this separate The protocol of the communication flow is different.
- Figure 1 shows a flow diagram of a method of identifying an application protocol in accordance with one embodiment of the present invention. This method is typically applied to network devices in data communication networks. As shown in FIG. 1, in this embodiment, the method for identifying an application protocol includes four steps Sl1, S12, S13, S14.
- step S1 the data packet to be detected is classified into a separate communication stream.
- step S12 a keyword in the payload of the communication stream is retrieved based on a keyword library of the identifiable application protocol, and a keyword weight vector of the communication stream is determined; wherein, the weight of one keyword is in a The location in the payload of the communication stream is related.
- the keywords of the hypertext transfer protocol include "http/”
- the keywords of the file transfer protocol include "ftp/"
- a communication stream whose key weight vector can be represented as v d .
- step S13 the similarity between the key weight vector of the communication stream and the feature key weight vector of the identifiable application protocol is determined.
- each identifiable protocol there are N identifiable protocols, and the feature key weight vector of each identifiable protocol can be represented as V n , « e ⁇ l, ⁇ , N ⁇ .
- step S14 if the predetermined condition is satisfied, an application protocol corresponding to the feature key weight vector having the highest similarity between the key weight vectors of the communication stream is determined as the application protocol of the communication stream.
- each identifiable application protocol may have the same keyword or keywords that do not overlap each other; the values of N and M are not necessarily Size relationship.
- each identifiable application protocol has at least one unique keyword, then M > N, which can improve the discrimination between different protocols.
- the data packet to be detected is to be classified according to a quintuple, where the quintuple includes: a source address, a destination address, a source port number, and a destination port. Number, transport protocol type.
- the data packet used to carry data between the source (node) and the destination (node) of the same application should have a source address, a destination address, a source port number, a destination port number, and a transport protocol type. identical.
- the source port number and the destination port number are different between packets of different applications; the source and destination addresses are different between packets between different sources (nodes) and destinations (nodes). Therefore, different packets with the same quintuple content should belong to the same application between a pair of sources and destinations and will be categorized into the same separate communication stream.
- the similarity in step S13 includes cosine similarity.
- cosine similarity between the keyword weight vector v d of the communication flow and the feature key weight vector of any identifiable protocol will be calculated separately and can be expressed as:
- the predetermined condition includes: the highest similarity is higher than a predetermined value.
- a predetermined value For example, the cosine similarity between the key weight vector v d of the communication stream / rf and the feature key weight vector V 2 is the highest, and the application protocol represented by V 2 when the highest similarity is higher than a predetermined value
- step S12 the higher the position of a keyword first appearing in the payload of a communication stream, the greater the weight.
- the identification process includes the above steps S1 l, S12, S13, S14, and the feature key weight vector of each identifiable protocol should be determined during the training process before the recognition process.
- 2 is a flow chart showing the determination of a feature key weight vector, that is, a training process, in a method of identifying an application protocol, in accordance with one embodiment of the present invention. as the picture shows, The training process includes two steps S21, S22.
- step S21 keywords in the payloads of the plurality of training communication streams are retrieved based on a keyword library of the identifiable application protocol, and key weight vectors of the plurality of training communication streams are determined.
- a feature key weight vector corresponding to each identifiable application protocol is determined according to the keyword weight vector of the plurality of training communication flows. Specifically, because the application protocol of each training communication flow is predicted, the keyword weight vector of all the training communication flows belonging to one application protocol may be averaged to determine the feature key weight corresponding to the application protocol. vector.
- step S21 the higher the position of a keyword first appearing in the payload of a communication stream, the greater the weight.
- the weight of the keyword is detected by the following itp-idf (reverse text position-reverse file frequency) algorithm, and the i-th keyword is for the jth
- itp-idf reverse text position-reverse file frequency
- the measure of the reverse text position /#, which is a measure of the reverse file frequency.
- the position may be a bit position or a byte position, the reciprocal of the representation; if there is no i key in the jth training communication stream Word, then the value is zero;
- the feature key weight vector corresponding to each identifiable application protocol is determined according to the keyword weight vector of the plurality of training communication flows.
- a feature key weight vector can be calculated from a given training communication flow, or can be called a centroid vector, as follows: Where E p represents the set of training communication flows belonging to protocol p,
- the feature key weight vector of each identifiable application protocol can be easily calculated based on the training communication stream.
- training the communication stream also categorizes a large number of training packets according to a quintuple; in the training communication stream, several communication streams for each identifiable application should be included.
- step S21 and step S22 may be repeatedly performed periodically or irregularly, and each time the execution is performed for the updated training communication flow to update the feature key of the identifiable application protocol.
- Word weight vector In a new training process, a new identifiable application protocol can be introduced; accordingly, the number of keywords in the keyword library may increase, and the updated training communication stream should also include the newly introduced identifiable application protocol. A number of communication flows, the update results also include a newly introduced feature key weight vector of the identifiable application protocol.
- step S12 in the identification process the same algorithm as in step S21 of the training process will be used to determine the key weight vector of the communication stream.
- itp id o id where ip indicates the position of the ith keyword when it first appears in the communication stream, and the position may be a bit position or a byte position, and the reciprocal represented by 3 ⁇ 4 ⁇ ; if no number appears in the communication stream i keyword ⁇ , then ⁇ ⁇ ,
- ⁇ , ⁇ 2 , , -, ⁇ ⁇ ) , where ⁇ represents the total number of keywords in the keyword library.
- the key to the protocol that identifies the communication flow is at the head of its payload.
- a keyword weight vector of a communication stream or a training communication stream is determined based on a content of a predetermined length of its payload header, and the keyword is retrieved.
- the weight calculation may be performed only in the content of the payload length of a predetermined length.
- the predetermined length is 128 bytes, or 256 bytes.
- the predetermined length of the payload header can be accommodated in one or more data packets.
- FIG. 3 shows a block diagram of a protocol identifying apparatus according to an embodiment of the present invention.
- the protocol identifying apparatus 10 in this embodiment includes: a first device 11, a second device 12, a third device 13, and a fourth device 14.
- the protocol identification device 10 is typically disposed in a network device in a data communication network.
- the first device 11 is configured to classify the data packet to be detected into a separate communication stream.
- a second device 12 configured to retrieve a keyword in a payload of the communication flow based on a keyword database of an identifiable application protocol, and determine a keyword weight vector of the communication flow; wherein, a keyword has a weight thereof It is related to the position in the payload of a communication stream.
- keywords in the keyword library of the identifiable application protocol there are a plurality of different keywords in the keyword library of the identifiable application protocol, and for each identifiable protocol, there are several keywords that may appear in the protocol, e ⁇ l ,... , M ⁇ .
- the keywords of the hypertext transfer protocol include "http/”
- the keywords of the file transfer protocol include "ftp/”, and the like.
- a communication stream whose key weight vector can be represented as v d .
- the third device 13 is configured to determine a similarity between the keyword weight vector of the communication stream and the feature key weight vector of the identifiable application protocol.
- each identifiable protocol there are N identifiable protocols, and the feature key weight vector of each identifiable protocol may be represented as V n , M e ⁇ l, . . . , N ⁇ .
- the fourth device 14 is configured to: determine, if the predetermined condition is met, an application protocol corresponding to the feature key weight vector having the highest similarity between the keyword weight vectors of the communication flow as an application protocol of the communication flow .
- different identifiable protocols may have the same keyword or keywords that do not overlap each other; the values of N and M do not have a necessary size relationship.
- each identifiable application protocol has at least one unique keyword, then 1 ⁇ >: ⁇ , which can improve the degree of discrimination between different protocols.
- the first device 11 classifies the data packet to be detected into a separate communication stream according to the quintuple, where the quintuple includes: a source address, a destination address, a source port number, Destination port number, transport protocol type.
- the quintuple includes: a source address, a destination address, a source port number, Destination port number, transport protocol type.
- a data packet for carrying data between a source (node) and a destination (node) of the same application protocol its source address, destination address, source port number, destination port number, and transport protocol type should be identical.
- the source port number and destination port number are different between packets of different application protocols; the source and destination addresses of packets between different sources (nodes) and destinations (nodes) are different. Therefore, different packets with the same quintuple content should belong to the same application protocol between a pair of sources and destinations and will be categorized into the same separate communication stream.
- the similarity determined by the third device 13 includes a cosine similarity.
- the cosine similarity between the keyword weight vector v d of the communication stream and the feature key weight vector of any identifiable protocol will be calculated separately and can be expressed as:
- the predetermined condition in the fourth device 14 includes: the highest similarity is higher than a predetermined value.
- the cosine similarity between the keyword weight vector v d of the communication flow and the feature key weight vector V 2 is the highest, and when the highest similarity is higher than a predetermined value, the application protocol represented by v 2 will An application protocol determined to be a communication flow; when the highest similarity is also lower than the predetermined value, the communication flow will be identified as an unknown protocol, that is, the communication flow is determined by the fourth device 14 to not belong to any Identifies the agreement.
- the identification process includes operations performed by the first device 11, the second device 12, the third device 13, and the fourth device 14, respectively, and characteristic keys of each identifiable protocol
- the weight vector should be predetermined during the training process prior to the identification process.
- the training process is performed by the second device 12 and includes two sub-operations 21, 22 (not shown).
- the second device 12 retrieves keywords in the payload of the plurality of training communication flows based on the keyword library of the identifiable application protocol, and determines the key weight vectors of the plurality of training communication flows.
- the second device 12 will determine a feature key weight vector corresponding to each identifiable application protocol based on the key weight vector of the plurality of training communication flows. Specifically, because the application protocol of each training communication flow is predicted, the keyword weight vector of all the training communication flows belonging to one application protocol may be averaged to determine the feature key weight corresponding to the application protocol. vector.
- the weight of the keyword is detected by using the itp-idf (reverse text position-reverse file frequency) algorithm as follows.
- itPij ⁇ ( 2 ) where represents the position of the ith keyword ⁇ when it first appears in the jth training communication stream, and the position may be a bit position or a byte position, represented.
- the reciprocal of y if the i-th keyword ⁇ does not appear in the jth training communication stream, the ⁇ value is zero;
- the second device 12 will determine a feature key weight vector corresponding to each identifiable application protocol based on the key weight vector of the plurality of training communication flows.
- a feature key weight vector can be calculated from a given training communication flow, or can be called a centroid vector, as follows:
- F p denotes a set of training communication flows belonging to protocol p
- Vj denotes a key weight vector of one communication flow in the set.
- v p can be obtained by averaging the weights of the keywords appearing in the key weight vector of each training communication stream in the set.
- training the communication stream also categorizes a large number of training packets according to a quintuple; in the training communication stream, several communication streams for each identifiable application should be included.
- the above training process that is, the sub-operation 21 and the sub-operation 22 performed by the second device 12, may be repeatedly performed periodically or irregularly, each time for the updated training communication flow, Update the feature key weight vector that identifies the application protocol.
- a new identifiable application protocol can be introduced; accordingly, the number of keywords in the keyword library may increase, and the updated training communication stream should also include the newly introduced identifiable application protocol.
- the update results also include a newly introduced feature key weight vector of the identifiable application protocol.
- the second device 12 will employ the same algorithm as in sub-operation 21 of the training process to determine the key weight vector for the communication stream.
- the second device 12 will use the itp-idf algorithm to communicate the key weight vector v d of the stream, and the ith keyword is for the communication flow.
- the weights are expressed as follows: ⁇ ⁇
- the bit The set can be a bit position or a byte position, and the reciprocal represented by 3 ⁇ 4 ⁇ ; if the i-th keyword does not appear in the communication stream ⁇ , ⁇ takes a value of zero. among them,
- M represents the total number of keywords in the keyword library.
- the key to the protocol that identifies the communication flow is at the head of its payload.
- the second device 11 performs a key weight vector of a communication stream or a training communication stream in a confirmation operation of a keyword weight vector in a recognition process or a sub-operation 21 in a training process. It will be determined based on the content of the predetermined length of its payload header.
- the second device 12 may perform keyword retrieval and weight calculation only in the content of the payload length of a predetermined length.
- the predetermined length is 128 bytes, or 256 bytes.
- the predetermined length of the payload header can be contained in one or more data packets.
- a network device provided with the above-described protocol identifying device 10 is provided.
- the network device is for example but not limited to: a switch, a router, a gateway, a terminal.
- the device referred to in the present invention may include: a software function module, a hardware module, or a combination of the two.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Communication Control (AREA)
Description
Claims
Priority Applications (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201080065034.9A CN102835090B (zh) | 2010-05-19 | 2010-05-19 | 应用协议识别方法及装置 |
| JP2013510470A JP5536280B2 (ja) | 2010-05-19 | 2010-05-19 | アプリケーションプロトコルを識別するための方法および装置 |
| US13/696,431 US9031959B2 (en) | 2010-05-19 | 2010-05-19 | Method and apparatus for identifying application protocol |
| EP10851576.8A EP2573995A4 (en) | 2010-05-19 | 2010-05-19 | Method and apparatus for identifying application protocol |
| PCT/CN2010/072923 WO2011143817A1 (zh) | 2010-05-19 | 2010-05-19 | 应用协议识别方法及装置 |
| KR1020127030076A KR101409563B1 (ko) | 2010-05-19 | 2010-05-19 | 애플리케이션 프로토콜 식별 방법 및 장치 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2010/072923 WO2011143817A1 (zh) | 2010-05-19 | 2010-05-19 | 应用协议识别方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2011143817A1 true WO2011143817A1 (zh) | 2011-11-24 |
Family
ID=44991164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2010/072923 Ceased WO2011143817A1 (zh) | 2010-05-19 | 2010-05-19 | 应用协议识别方法及装置 |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US9031959B2 (zh) |
| EP (1) | EP2573995A4 (zh) |
| JP (1) | JP5536280B2 (zh) |
| KR (1) | KR101409563B1 (zh) |
| CN (1) | CN102835090B (zh) |
| WO (1) | WO2011143817A1 (zh) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2487800A (en) * | 2011-02-03 | 2012-08-08 | Roke Manor Research | Communication analysis |
| CN105007194A (zh) * | 2015-05-25 | 2015-10-28 | 上海南邮实业有限公司 | 一种自动识别网络协议的方法 |
| CN105024993A (zh) * | 2015-05-25 | 2015-11-04 | 上海南邮实业有限公司 | 一种基于向量运算的协议比对方法 |
| CN108234452A (zh) * | 2017-12-12 | 2018-06-29 | 上海天旦网络科技发展有限公司 | 一种网络数据包多层协议识别的系统和方法 |
| US11178027B1 (en) * | 2014-09-04 | 2021-11-16 | HCA Holdings, Inc. | Differential processing of data streams based on protocols |
| US12124861B1 (en) | 2018-08-20 | 2024-10-22 | C/Hca, Inc. | Disparate data aggregation for user interface customization |
| US12272448B1 (en) | 2020-02-18 | 2025-04-08 | C/Hca, Inc. | Predictive resource management |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8943039B1 (en) * | 2006-08-25 | 2015-01-27 | Riosoft Holdings, Inc. | Centralized web-based software solution for search engine optimization |
| US9344384B2 (en) * | 2012-11-13 | 2016-05-17 | Netronome Systems, Inc. | Inter-packet interval prediction operating algorithm |
| CN103166963A (zh) * | 2013-03-05 | 2013-06-19 | 汉柏科技有限公司 | 一种解除封装的协议识别方法及系统 |
| CN103414600B (zh) * | 2013-07-19 | 2017-03-08 | 华为技术有限公司 | 近似匹配方法和相关设备及通信系统 |
| CN103716187B (zh) * | 2013-12-20 | 2017-03-29 | 新浪网技术(中国)有限公司 | 网络拓扑结构确定方法和系统 |
| US10116493B2 (en) | 2014-11-21 | 2018-10-30 | Cisco Technology, Inc. | Recovering from virtual port channel peer failure |
| US10333828B2 (en) | 2016-05-31 | 2019-06-25 | Cisco Technology, Inc. | Bidirectional multicasting over virtual port channel |
| US11509501B2 (en) * | 2016-07-20 | 2022-11-22 | Cisco Technology, Inc. | Automatic port verification and policy application for rogue devices |
| US10701086B1 (en) | 2016-07-28 | 2020-06-30 | SlashNext, Inc. | Methods and systems for detecting malicious servers |
| US10193750B2 (en) | 2016-09-07 | 2019-01-29 | Cisco Technology, Inc. | Managing virtual port channel switch peers from software-defined network controller |
| US10764313B1 (en) * | 2017-01-24 | 2020-09-01 | SlashNext, Inc. | Method and system for protection against network-based cyber threats |
| US10547509B2 (en) | 2017-06-19 | 2020-01-28 | Cisco Technology, Inc. | Validation of a virtual port channel (VPC) endpoint in the network fabric |
| CN109873838A (zh) * | 2019-04-19 | 2019-06-11 | 国网甘肃省电力公司电力科学研究院 | 一种新能源厂站远程运维非法网络通道识别方法 |
| CN110138681B (zh) * | 2019-04-19 | 2021-01-22 | 上海交通大学 | 一种基于tcp报文特征的网络流量识别方法及装置 |
| CN110460488B (zh) * | 2019-07-01 | 2022-10-18 | 华为技术有限公司 | 业务流识别方法和装置、模型生成方法和装置 |
| CN111797239B (zh) * | 2020-09-08 | 2021-01-15 | 中山大学深圳研究院 | 应用程序的分类方法、装置及终端设备 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101184089A (zh) * | 2007-12-14 | 2008-05-21 | 浙江工业大学 | 一种基于端口与内容混杂检测的协议识别方法 |
| CN101488861A (zh) * | 2008-12-19 | 2009-07-22 | 中山大学 | 一种网络未知应用的关键词提取方法 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6591299B2 (en) * | 1997-11-25 | 2003-07-08 | Packeteer, Inc. | Method for automatically classifying traffic with enhanced hierarchy in a packet communications network |
| US6412000B1 (en) * | 1997-11-25 | 2002-06-25 | Packeteer, Inc. | Method for automatically classifying traffic in a packet communications network |
| WO2001001272A2 (en) * | 1999-06-30 | 2001-01-04 | Apptitude, Inc. | Method and apparatus for monitoring traffic in a network |
| US8010469B2 (en) * | 2000-09-25 | 2011-08-30 | Crossbeam Systems, Inc. | Systems and methods for processing data flows |
| US20020186697A1 (en) * | 2001-04-23 | 2002-12-12 | Thakkar Bina Kunal | Protocol encoder and decoder |
| US20090010259A1 (en) * | 2007-07-08 | 2009-01-08 | Alexander Sirotkin | Device, system, and method of classification of communication traffic |
| US8494000B1 (en) * | 2009-07-10 | 2013-07-23 | Netscout Systems, Inc. | Intelligent slicing of monitored network packets for storing |
-
2010
- 2010-05-19 CN CN201080065034.9A patent/CN102835090B/zh not_active Expired - Fee Related
- 2010-05-19 US US13/696,431 patent/US9031959B2/en not_active Expired - Fee Related
- 2010-05-19 JP JP2013510470A patent/JP5536280B2/ja not_active Expired - Fee Related
- 2010-05-19 WO PCT/CN2010/072923 patent/WO2011143817A1/zh not_active Ceased
- 2010-05-19 EP EP10851576.8A patent/EP2573995A4/en not_active Withdrawn
- 2010-05-19 KR KR1020127030076A patent/KR101409563B1/ko not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101184089A (zh) * | 2007-12-14 | 2008-05-21 | 浙江工业大学 | 一种基于端口与内容混杂检测的协议识别方法 |
| CN101488861A (zh) * | 2008-12-19 | 2009-07-22 | 中山大学 | 一种网络未知应用的关键词提取方法 |
Non-Patent Citations (3)
| Title |
|---|
| CHEN, LIANG ET AL.: "A survey of Application-level Protocol Identification Algorithm", COMPUTER SCIENCE, vol. 34, no. 7, 2007, pages 73 - 75, XP008162754 * |
| See also references of EP2573995A4 * |
| SEN, SUBHABRATA ET AL.: "Accurate, Scalable In-Network Identification of P2P Traffic Using Application Signatures", WWW2004, 22 May 2004 (2004-05-22), pages 512 - 517, XP002389082 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2487800A (en) * | 2011-02-03 | 2012-08-08 | Roke Manor Research | Communication analysis |
| US8924531B2 (en) | 2011-02-03 | 2014-12-30 | Roke Manor Research Limited | Determining communication sessions having the same protocol structure |
| GB2487800B (en) * | 2011-02-03 | 2018-07-04 | Roke Manor Res Limited | A method and apparatus for communications analysis |
| US11178027B1 (en) * | 2014-09-04 | 2021-11-16 | HCA Holdings, Inc. | Differential processing of data streams based on protocols |
| US11431595B1 (en) | 2014-09-04 | 2022-08-30 | C/Hca, Inc. | Differential processing of data streams based on protocols |
| CN105007194A (zh) * | 2015-05-25 | 2015-10-28 | 上海南邮实业有限公司 | 一种自动识别网络协议的方法 |
| CN105024993A (zh) * | 2015-05-25 | 2015-11-04 | 上海南邮实业有限公司 | 一种基于向量运算的协议比对方法 |
| CN108234452A (zh) * | 2017-12-12 | 2018-06-29 | 上海天旦网络科技发展有限公司 | 一种网络数据包多层协议识别的系统和方法 |
| CN108234452B (zh) * | 2017-12-12 | 2020-11-24 | 上海天旦网络科技发展有限公司 | 一种网络数据包多层协议识别的系统和方法 |
| US12124861B1 (en) | 2018-08-20 | 2024-10-22 | C/Hca, Inc. | Disparate data aggregation for user interface customization |
| US12602238B1 (en) | 2018-08-20 | 2026-04-14 | C/Hca, Inc. | Disparate data aggregation for user interface customization |
| US12272448B1 (en) | 2020-02-18 | 2025-04-08 | C/Hca, Inc. | Predictive resource management |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102835090A (zh) | 2012-12-19 |
| EP2573995A4 (en) | 2017-07-26 |
| JP2013526804A (ja) | 2013-06-24 |
| KR20130017089A (ko) | 2013-02-19 |
| KR101409563B1 (ko) | 2014-06-19 |
| EP2573995A1 (en) | 2013-03-27 |
| US20130054619A1 (en) | 2013-02-28 |
| JP5536280B2 (ja) | 2014-07-02 |
| US9031959B2 (en) | 2015-05-12 |
| CN102835090B (zh) | 2015-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2011143817A1 (zh) | 应用协议识别方法及装置 | |
| CN100556031C (zh) | 智能集成网络安全设备 | |
| US12223406B2 (en) | System and method for determining device attributes using a classifier hierarchy | |
| JP5362669B2 (ja) | ネットワークパケットの効率的な分類 | |
| US8448234B2 (en) | Method and apparatus for deep packet inspection for network intrusion detection | |
| TWI729320B (zh) | 可疑封包偵測裝置及其可疑封包偵測方法 | |
| US12184681B2 (en) | Cyberattack detection with topological data | |
| Thaseen et al. | Network intrusion detection using machine learning techniques | |
| EP2725512B1 (en) | System and method for malware detection using multi-dimensional feature clustering | |
| Rao et al. | Tor anonymous traffic identification based on gravitational clustering | |
| WO2008002930A2 (en) | Packet classification in a network security device | |
| CN104509063A (zh) | 改善低延时高吞吐量网络中双向访问控制列表的硬件利用率 | |
| US20230412618A1 (en) | Stack-hac for machine learning based botnet detection | |
| CN102217248B (zh) | 分布式分组流检查和处理 | |
| Ye et al. | P2P and P2P botnet traffic classification in two stages | |
| CN113382039A (zh) | 一种基于5g移动网络流量分析的应用识别方法和系统 | |
| CN109257384B (zh) | 基于访问节奏矩阵的应用层DDoS攻击识别方法 | |
| TWI797962B (zh) | 基於SASE的IPv6雲邊緣網路安全連線方法 | |
| Fu et al. | Network storage covert channel detection based on data joint analysis | |
| Haefner et al. | Trust and verify: A complexity-based IoT behavioral enforcement method | |
| JP2007228217A (ja) | トラフィック判定装置、トラフィック判定方法、及びそのプログラム | |
| JP5520650B2 (ja) | P2p端末検知装置、p2p端末検知方法、およびp2p端末検知システム | |
| Haefner et al. | Trust and Verify: A Complexity-Based | |
| CN116055073A (zh) | 一种僵尸主机检测方法、装置、设备以及存储介质 | |
| Anantavrasilp | A unified framework for flow classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WWE | Wipo information: entry into national phase |
Ref document number: 201080065034.9 Country of ref document: CN |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10851576 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 13696431 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 9593/CHENP/2012 Country of ref document: IN |
|
| ENP | Entry into the national phase |
Ref document number: 20127030076 Country of ref document: KR Kind code of ref document: A Ref document number: 2013510470 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2010851576 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |




