Abnormal group detection method based on weighted dynamic network representation learning

Abstract

The invention belongs to the technical field of dynamic network anomaly detection, and discloses an abnormal group detection method based on weighted dynamic network representation learning, which comprises the following steps: step 1, constructing a weighted dynamic network representation learning model based on a deep self-encoding neural network; 2, performing abnormal link identification basedon the constructed weighted dynamic network representation learning model to obtain an abnormal link set; and 3, constructing a full-connection neural network model based on the abnormal link set, and performing abnormal group detection through the full-connection neural network model. According to the method, the exception link is combined with the full-connection neural network exception detection model, the application range of the method is expanded on the basis of the exception link, experimental verification is carried out on a secure mail data set and an AS-level Internet data set, andexperimental results show that the method has a good exception group detection effect.

Description

technical field [0001] The invention belongs to the technical field of dynamic network anomaly detection, in particular to an abnormal group detection method based on weighted dynamic network representation learning. Background technique [0002] With the rapid development of network technology and the widespread popularization of computers and mobile smart terminals, the network has greatly changed people's work and life. At the same time, the scale of the network has become larger and more complex. This makes it more and more difficult to detect anomalies in dynamic networks. It is difficult to fully capture the structural features in the graph based on the existing statistical methods of graph structure features. How to effectively identify abnormal groups in changing networks is a current research hotspot. [0003] The basic idea of ​​network representation learning is to convert the nodes in the network into multi-dimensional vector representations through a series of ...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the problem that the existing network representation learning method cannot learn the corresponding relationship between edges and weights well when facing the weighted dynamic network, and cannot effectively identify the abnormal weight when performing abnormal link detection, and proposes a method based on weighted dynamic Anomaly Group Detection Method for Network Representation Learning

Images