Intelligent Advanced Attack Detection Technology based on Multi-modal Data Fusion

Authors

  • Feilu Hang Information security operation and maintenance center of Information Center of Yunnan Power Grid Co., LTD., Kunming, Yunnan, 650106, China
  • Linjiang Xie Information security operation and maintenance center of Information Center of Yunnan Power Grid Co., LTD., Kunming, Yunnan, 650106, China
  • Zhenhong Zhang Network Security Management Center of Information Center of Yunnan Power Grid Co., LTD., Kunming, Yunnan, 650106, China
  • Jian Hu Network Security Management Center of Information Center of Yunnan Power Grid Co., LTD., Kunming, Yunnan, 650106, China

DOI:

https://doi.org/10.12694/scpe.v25i4.2862

Keywords:

Wireless sensor network; Information fusion; Intrusion detection; Convolutional neural network; Anomaly information extraction

Abstract

This paper proposes an adaptive Wedman intrusion detection algorithm (AID-DFS) for data fusion. Firstly, feature extraction of abnormal text detection is carried out using a BI-gated loop (Bi-GRU). Multi-branch convolutional recurrent neural network (CNN-RNN) extracts hierarchical features from abnormal images. The multi-mode dynamic fusion uses the intermodal and intramodal attention mechanisms. In this way, a joint representation of multiple modes is obtained. The visual perception mechanism is used to realize multichannel integration and strengthen the function of original information in multichannel. The experimental results show that the proposed method has 99.6% accuracy and 94.9% accuracy. Compared with other algorithms, the proposed method can improve the performance of the intrusion system by about 10.2%.

Downloads

Published

2024-06-16

Issue

Vol. 25 No. 4 (2024)

Section

Special Issue - Graph Powered Big Aerospace Data Processing