A network traffic classification and application identification method for automatic mining of bit-granularity features
A network traffic and network application technology, applied in the field of automatic mining of bit granularity characteristics in specified application traffic, can solve problems such as loss of effectiveness, time-consuming and labor-intensive, inability to update and apply in time, and achieve good network security, improve accuracy and The effect of reliability
Active Publication Date: 2019-06-14
深圳赋乐科技集团有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, with the increasing complexity and concealment of network applications in Internet traffic, the traditional network traffic classification method based on byte-granularity feature matching gradually loses its effectiveness.
At the same time, with the continuous growth of the number of network applications and the increasingly frequent version updates, the traditional method of relying on manual discovery of features cannot be updated and applied in time due to time-consuming and labor-intensive, resulting in extremely difficult tasks for accurate classification of network traffic and application identification. big challenge
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] In order to solve the difficult problems of network traffic classification and application identification, the present invention proposes a network traffic application classification and identification method based on bit granularity, and provides its automatic feature mining method, which mainly includes the following five steps: S1. Create a designated network Application Flow Matters Database D old ; S2. Establish a designated hash table Bit-Table, generate a new item database D new ;S3. Build based on D new The prefix tree Miner-Tree; S4. Pruning based on minimum support and minimum confidence to form bit-granularity features; S5. Network application traffic identification based on bit-granularity features. The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a network flow classification and application identification method for automatically excavating bit granularity characteristic. The method comprises: a step 1 of creating an item database Dold of appointed network application flow; a step 2 of establishing an appointed Hash table Bit-Table and generating a new item database Dnew; a step 3 of constructing a prefix tree Miner-Tree based on the Dnew; a step 4 of forming a bit granularity characteristic on the basis of pruning with minimum support and minimum confidence; and a step 5 of identifying network application flow based on the bit granularity characteristic.
Description
technical field [0001] The invention relates to network traffic classification technology, in particular to a bit granularity-based network traffic classification technology and a method for automatically mining bit granularity features in specified application traffic. Background technique [0002] With the continuous development of Internet technology and the continuous growth of network users, network traffic identification and classification methods based on feature matching have played an extremely important role in network management and security auditing due to their accuracy and stability, such as network services Quality optimization and network intrusion detection, etc. However, with the increasing complexity and concealment of network applications in Internet traffic, the traditional network traffic classification method based on byte-granularity feature matching gradually loses its effectiveness. At the same time, with the continuous growth of the number of netw...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L12/26
CPCH04L43/04H04L43/062
Inventor 王秋晨
Owner 深圳赋乐科技集团有限公司