A hijacking traffic identification method, device and electronic equipment

Abstract

The embodiment of this specification discloses a hijacking traffic identification method, device, and electronic equipment, wherein, after receiving the traffic to be identified, the method can obtain multiple first access subjects related to the traffic to be identified in the first historical period The access data within the first access subject and make statistics to determine the time series of the values ​​of at least one statistical indicator under the plurality of first access subjects in the preset period in chronological order, and obtain multiple time series; based on the multiple The time series constructs the feature matrix of the traffic to be identified and inputs it into the preset convolutional neural network to obtain the evaluation parameters of whether the traffic to be identified belongs to hijacking traffic. The preset convolutional neural network is trained based on the feature matrix of the sample traffic. The construction method of the characteristic matrix of the traffic is consistent with the construction method of the characteristic matrix of the traffic to be identified; finally, based on the evaluation parameters, it can be identified whether the traffic to be identified belongs to hijacking traffic.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a hijacking traffic identification method, device and electronic equipment. Background technique [0002] With the development of network technology and terminal technology, more and more users obtain information by accessing traffic hosts, making some traffic hosts master a large amount of traffic, which attracts a large number of network content hosts to deliver relevant network content to users through these traffic hosts (For example, advertisers place advertisements to users through traffic hosts) to get the expected conversion, and traffic hosts can also obtain corresponding benefits. [0003] However, for economic benefit, some traffic owners will use fraudulent methods such as traffic hijacking to forge traffic, thereby deceiving network content producers to obtain more income, such as hackers or developers controlling broiler device clicks through viruses and...

AI Technical Summary

Problems solved by technology

[0003] However, for economic benefit, some traffic owners will use fraudulent methods such as traffic hijacking to forge traffic, thereby deceiving network content producers to obtain more income, such as hackers or developers controlling broiler device clicks through viruses and malware, accessing advertisements and setting Take advertising costs, which will cause great losses to network content producers

Images