DoS attack detection method oriented to software defined network
A software-defined network, software-oriented technology, applied in the direction of electrical components, transmission systems, etc., can solve the problems of slow convergence speed and long training time of SOM algorithm, and achieve the effect of real-time and accurate detection
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0051] Example one:
[0052] Such as figure 1 As shown, a software-defined network-oriented DoS attack detection method of the present invention includes the following steps:
[0053] Step S101: Use the three statistical attributes of single-stream scale SSF, stream address growth rate AGS, and flow table matching rate RSM as the DoS attack detection characteristics of the software-defined network, and mark historical traffic of the collected DoS attacks of the software-defined network Data feature extraction and calculation;
[0054] Step S102: Use a linear function standardization method and a mutation progression method to standardize and normalize the historical flow data after feature extraction and calculation, to obtain standardized and normalized historical flow data;
[0055] Step S103: Use standardized and normalized historical traffic data as a training data set, and use a conditional random field algorithm to construct a software-defined network DoS attack traffic classif...
Example Embodiment
[0057] Embodiment two:
[0058] Such as figure 2 As shown, another software-defined network-oriented DoS attack detection method of the present invention includes the following steps:
[0059] Step S201: Add a mark to the collected historical traffic data of the DoS attack of the software-defined network, and mark it as 0 when it is normal, and mark it as 1 when it is abnormal.
[0060] Step S202: Use the three strongly representative statistical attributes of single-stream scale SSF, stream address growth rate AGS, and stream table matching rate RSM as the detection characteristics of the software-defined network DoS attack, and the collected software-defined network DoS attack Feature extraction and calculation of marked historical traffic data;
[0061] The SSF (Size of a Single Flow) describes the size of each data flow entering the SDN network, including two attribute parameters: the number of flow packets and the number of flow bytes, the average number of flow packets ANPF (a...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap