Title:
ENCRYPTED MALICIOUS TRAFFIC DETECTION METHOD AND APPARATUS, STORAGE MEDIUM AND ELECTRONIC APPARATUS
Document Type and Number:
WIPO Patent Application WO/2023/056808
Kind Code:
A1
Abstract:
Embodiments provide an encrypted malicious traffic detection method and apparatus, a storage medium and an electronic apparatus, the method comprising: extracting various messages of a predetermined number of training samples (S302); extracting different key fields from the various messages of the predetermined number of training samples, and forming the extracted key fields into a predetermined number of word vectors (S304); constructing a target BiLSTM model according to the predetermined number of word vectors by using multi-head attention and BiLSTM means (S306); and carrying out encrypted malicious traffic detection according to the target BiLSTM model (S308), which may solve the problem in the related technology that in the malicious traffic detection method, extracting the first m bytes of traffic as an input is only a simple slice of traffic bytes, and the accurate semantics of the traffic cannot be learned, leading to a poor detection effect of malicious encrypted traffic. By using multi-head attention means, the weight of the key fields is increased, and forward and backward long-distance dependencies are obtained by means of BiLSTM, so as to achieve a better encrypted malicious traffic detection effect.
Inventors:
WANG JIGANG (CN)
GU YONGHAO (CN)
ZHANG XIAOQING (CN)
XU HAO (CN)
HUANG ZEQI (CN)
WANG YIFEI (CN)
TIAN TIAN (CN)
WANG JING (CN)
MA SUAN (CN)
FU PENG (CN)
GU YONGHAO (CN)
ZHANG XIAOQING (CN)
XU HAO (CN)
HUANG ZEQI (CN)
WANG YIFEI (CN)
TIAN TIAN (CN)
WANG JING (CN)
MA SUAN (CN)
FU PENG (CN)
Application Number:
PCT/CN2022/116590
Publication Date:
April 13, 2023
Filing Date:
September 01, 2022
Export Citation:
Assignee:
ZTE CORP (CN)
UNIV BEIJING POSTS & TELECOMM (CN)
UNIV BEIJING POSTS & TELECOMM (CN)
International Classes:
G06F21/00
Foreign References:
| CN112307473A | 2021-02-02 | |||
| CN112926303A | 2021-06-08 | |||
| CN111241294A | 2020-06-05 | |||
| CN112487109A | 2021-03-12 | |||
| US11017173B1 | 2021-05-25 |
Other References:
LIU, YONGQIANG; XU, YI; HE, YONG-HUI; LIU, WEN-BIN: "Wind Power Prediction Method Based on Bidirectional long-Short Term Memory Neural Network", TIANJIN-LIGONG-DAXUE-XUEBAO = JOURNAL OF TIANJIN UNIVERSITY OF TECHNOLOGY, TIANJIN UNIVERSITY OF TECHNOLOGY, CN, vol. 36, no. 5, 31 October 2020 (2020-10-31), CN , pages 49 - 54, 59, XP009546252, ISSN: 1673-095X, DOI: 10.3969/j.issn.1673-095X.2020.05.011
SUN TINGTING; ZHANG CHUNHONG; JI YANG; HU ZHENG: "MSnet: Multi-Head Self-Attention Network for Distantly Supervised Relation Extraction", IEEE ACCESS, IEEE, USA, vol. 7, 1 January 1900 (1900-01-01), USA , pages 54472 - 54482, XP011723422, DOI: 10.1109/ACCESS.2019.2913316
SUN TINGTING; ZHANG CHUNHONG; JI YANG; HU ZHENG: "MSnet: Multi-Head Self-Attention Network for Distantly Supervised Relation Extraction", IEEE ACCESS, IEEE, USA, vol. 7, 1 January 1900 (1900-01-01), USA , pages 54472 - 54482, XP011723422, DOI: 10.1109/ACCESS.2019.2913316
Attorney, Agent or Firm:
KANGXIN PARTNERS, P.C. (CN)
Download PDF:
Previous Patent: STORAGE BOX APPLIED TO ASSEMBLING AND DEBUGGING OF RADIO FREQUENCY CIRCUIT
Next Patent: POSITIONING METHOD, APPARATUS, AND SYSTEM
Next Patent: POSITIONING METHOD, APPARATUS, AND SYSTEM