Sampling-based edge computing architecture Internet of Things intrusion detection system and method

Abstract

The invention discloses a sampling-based edge computing architecture internet of things intrusion detection system and method. The method is applied to the edge computing architecture Internet of Things, and comprises a network traffic quality discriminator used for selecting a network traffic data packet feature vector of a preset size according to a round from a network traffic training data set of a specific batch, selecting a network by a network traffic data packet, and determining the network traffic quality. And the judgment module is used for judging whether the network flow data packet selected by the flow data packet selection network is malicious or not according to the feature vector. According to the system provided by the invention, the network combination is selected through the network flow quality discriminator and the network flow data packet, so that the automatic sampling detection of the data packet is realized without the interference of external personnel, and the stability of the edge computing architecture Internet of Things intrusion detection system facing a large amount of data is improved; and the resource consumption of the edge computing architecture Internet of Things intrusion detection system can be saved, and the performance of the edge computing architecture Internet of Things intrusion detection system is improved.

Description

technical field [0001] The invention belongs to the field of Internet of Things security, and more specifically relates to a sampling-based edge computing architecture Internet of Things intrusion detection system and method. Background technique [0002] As a new type of network architecture, edge computing uses surrounding edge servers that can provide network, computing, storage, application and other capabilities to provide various services and applications nearby, effectively solving the delay problem in IoT applications and improving Improve network performance, reduce operating costs, and ensure rational use of resources. However, in today's environment where the Internet of Things is becoming more and more popular, a large number of heterogeneous Internet of Things devices bring a large amount of private data, which exist in different locations, and it is difficult to ensure integrity; in addition, unauthorized users or opponents may Modifying or misusing the upload...

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a sampling-based edge computing framework IoT intrusion detection system and method, the purpose of which is to use the potential timing characteristics of network traffic to sample and select network traffic data packets for intrusion Detection, obtain the overall detection results of a batch of network traffic data, reduce the amount of calculation to adapt to the edge computing architecture, thereby solving the data expansion of the existing Internet of Things intrusion detection system, resulting in relatively low efficiency of intrusion detection, which cannot be used for quartz edge computing Architecture Technical Issues

Images