Data security transmission method and system of embedded AI chip on edge side of unmanned aerial vehicle

Abstract

The application provides a method and system for secure data transmission of an embedded AI chip on the edge side of a UAV. The embedded AI chip generates a first unique identifier corresponding to the embedded AI chip, and encrypts the first unique identifier to generate and identify it. string, and send the encrypted identification string to the server. The server obtains the program information of the embedded AI chip, generates the second unique identifier corresponding to the embedded AI chip, and compares the second unique identifier with the first unique identifier. If the comparison results are consistent, the verification is passed, and the server generates a dynamic The 3DES encryption key and dynamic 3DES decryption key are encapsulated into a response message and returned to the embedded AI chip. In this way, the embedded AI chip can use the dynamic 3DES encryption key and dynamic 3DES decryption key to encrypt or decrypt the data interacted with the server, thereby improving the security of data interaction between the drone and the server .

Description

technical field [0001] The present application relates to the technical field of unmanned aerial vehicles, in particular, to a method and system for secure data transmission of an embedded AI chip on the edge side of an unmanned aerial vehicle. Background technique [0002] With the development of AI technology, the degree of optimization of AI algorithms is increasing day by day, which enables AI algorithms to run in terminal devices with embedded AI chips in the form of edge computing. Taking drones as an example, drones with embedded AI chips can independently perform some data processing tasks without relying on the server, for example, analyze images to perform target tracking, route planning, flight obstacle avoidance, etc. action. [0003] However, the processing capability of the embedded AI chip on the edge side is limited after all. In some cases, the embedded AI still needs to interact with the server for data, such as the upgrade of the AI ​​processing model, th...

AI Technical Summary

Problems solved by technology

[0003] However, the processing capability of the embedded AI chip on the edge side is limited after all. In some cases, the embedded AI still needs to interact with the server for data, such as the upgrade of the AI ​​processing model, the reporting of some data logs, and cannot be processed by edge computing. data upload, etc.

Moreover, the data security protection capability of the embedded AI chip on the edge side is also limited. The embedded AI chip itself or its data interaction process with the server may be illegally invaded, affecting the security of the entire system.

Images