Title:
METHOD FOR GENERATING NETWORK FLOW ANOMALY DETECTION MODEL, AND COMPUTER DEVICE
Document Type and Number:
WIPO Patent Application WO/2022/037191
Kind Code:
A1
Abstract:
Provided are a method for generating a network flow anomaly detection model, and a computer device. The method for generating a network flow anomaly detection model comprises: training a first network model on the basis of a source domain, so as to obtain a trained first network model, wherein the trained first network model comprises a source domain feature extractor and a classifier; training a second network model on the basis of a target domain, the source domain, the source domain feature extractor and a discriminator, so as to obtain a target domain feature extractor; and generating a network flow anomaly detection model according to the target domain feature extractor and the classifier. In the present invention, by means of training, a feature extracted on a target domain by a target domain feature extractor is similar to a feature extracted on a source domain by a source domain feature extractor, and furthermore, a classifier, which is obtained by performing training on the basis of the source domain, in the network flow anomaly detection model in the present invention can perform anomaly detection on the target domain, and has high accuracy.
Inventors:
LV QI (CN)
LI WEICHAO (CN)
WANG YI (CN)
JIN BO (CN)
LI WEICHAO (CN)
WANG YI (CN)
JIN BO (CN)
Application Number:
PCT/CN2021/098695
Publication Date:
February 24, 2022
Filing Date:
June 07, 2021
Export Citation:
Assignee:
PENG CHENG LAB (CN)
UNIV SOUTHERN SCI & TECH (CN)
UNIV SOUTHERN SCI & TECH (CN)
International Classes:
H04L29/06
Foreign References:
| CN111683108A | 2020-09-18 | |||
| CN109376620A | 2019-02-22 | |||
| CN110149280A | 2019-08-20 | |||
| CN111444952A | 2020-07-24 | |||
| US20200193269A1 | 2020-06-18 |
Other References:
WANG QI; GAO JUNYU; LI XUELONG: "Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes", IEEE TRANSACTIONS ON IMAGE PROCESSING, IEEE, USA, vol. 28, no. 9, 1 September 2019 (2019-09-01), USA, pages 4376 - 4386, XP011733034, ISSN: 1057-7149, DOI: 10.1109/TIP.2019.2910667
Attorney, Agent or Firm:
JOHNSON INTELLECTUAL PROPERTY AGENCY (SHENZHEN) (CN)
Download PDF:
Previous Patent: BONE CONDUCTED MUSIC DENTAL CLEANING DEVICE
Next Patent: DOMAIN CONTROL-BASED BATTERY MANAGEMENT SYSTEM
Next Patent: DOMAIN CONTROL-BASED BATTERY MANAGEMENT SYSTEM