Internet of Things device identification method based on spontaneous flow

Abstract

The invention discloses an Internet of Things device identification method based on spontaneous flow. According to the invention, representative characteristics of spontaneous flow are matched to a time sequence, an Internet of Things device identification problem is converted into a signal processing problem, and a convolutional neural network is used to analyze a time sequence result matched with the representative characteristics, so an Internet of Things device identification problem based on flow analysis is solved. In network management, the Internet of Things device type can be accurately identified based on flow analysis, and the access number of Internet of Things devices of the same type behind an intranet can be accurately estimated, so the automatic management of device assetsand security policy configuration are helped, and the method has great significance in security supervision of the Internet of Things devices.

Description

technical field [0001] The invention belongs to the technical field of Internet of Things device identification, and in particular relates to a method for identifying Internet of Things devices based on spontaneous traffic. Background technique [0002] At present, due to the large number of devices, various types, and limited security functions, IoT technology faces security risks such as software and hardware failures, physical attacks, information leakage or tampering, unauthorized access, or malicious control. The security of IoT devices will affect people's IoT life, therefore, the security issues in IoT technology must be properly handled. [0003] In order to solve the security problems of IoT devices, the current common solutions can be divided into the following two types: [0004] Set up an intrusion detection system and upgrade IoT devices. These two solutions are less efficient in detecting real-time updated attacks. At the same time, this requires high system ...

AI Technical Summary

Problems solved by technology

These two solutions are less efficient in detecting real-time updated attacks. At the same time, this requires high system updates for suppliers, which is time-consuming and labor-intensive, and cannot cope with the current rapidly developing IoT market.

In addition, malicious intruders can easily develop some malicious software based on the current loopholes in the IoT market, leading to attacks on IoT systems and causing security losses