Unlock instant, AI-driven research and patent intelligence for your innovation.

Fast encryption and decryption-oriented car networking key management method based on reinforcement learning

A technology of intensive learning and key management, which is applied in the field of key management of the Internet of Vehicles for fast encryption and decryption, can solve the problems of roadside units that are not completely trusted facilities, reduce authentication overhead, etc., and achieve improved anti-eavesdropping interception rate, Effects of preventing data leakage and eavesdropping attacks

Active Publication Date: 2021-07-16
XIAMEN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Y.Hao et al [Y.Hao, Y.Cheng, C.Zhou, and W.Song, "A distributed key management framework with cooperative message authentication in VANETs," IEEE J.Sel.Areas Commun., vol.29, no .3, pp.616–629, Mar.2011] proposed a distributed key management scheme based on group signatures, using roadside units to distribute keys, and using cooperative message authentication protocols to reduce authentication overhead, but roadside units are not completely Trusted facility, as a key distributor, it is easy to cause new security problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fast encryption and decryption-oriented car networking key management method based on reinforcement learning
  • Fast encryption and decryption-oriented car networking key management method based on reinforcement learning
  • Fast encryption and decryption-oriented car networking key management method based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical solutions of the present invention will be further described below in conjunction with the examples.

[0024] Embodiments of the present invention include the following steps:

[0025] Step 1: Establish a vehicle networking network, including one roadside unit, vehicle i, the current number n of vehicles is 20, and one active bug. The vehicle uses the AES encryption algorithm to encrypt communication information. There are three optional key lengths, namely l∈{128,192,256}, and the power of the active eavesdropper p∈[0,5]mW, which is quantized to 11 levels, namely p∈[0, 0.5,...,5].

[0026] Initialization parameters: the number of roadside unit states G is 100, the number of behaviors H is 80, learning factor α=0.5, discount factor γ=0.5, learning rate δ 1 = 0.1 and δ 2 =0.05, key length coefficient a=0.8, received interference power coefficient b=0.5, security level coefficient c 1 =0.7, risk level coefficient c 2 =0.4, the key update delay coefficie...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A fast encryption and decryption-oriented car networking key management method based on reinforcement learning, involving car networking communication and security. Aiming at the personalized communication needs of Internet of Vehicles users and preventing data leakage, a key management method for Internet of Vehicles oriented to fast encryption and decryption based on reinforcement learning is designed. Based on information such as interference power received by vehicles in the Internet of Vehicles, key duration, and vehicle density, the method uses reinforcement learning to continuously optimize the vehicle key update frequency and key length to prevent data leakage. The proposed method can adapt to the dynamic Internet of Vehicles environment and prevent eavesdropping attacks, improve the anti-eavesdropping interception rate of vehicle communication, and reduce the delay of secure communication.

Description

technical field [0001] The present invention relates to a method in the field of vehicle networking communication and security technologies, in particular to a reinforcement learning-based fast encryption and decryption-oriented vehicle networking key management method. Background technique [0002] As an important self-organizing network for information exchange, the Internet of Vehicles provides vehicle users with information such as location, road safety, and weather, and improves the driving experience and safety level of vehicle users. However, due to the openness and high dynamics of the Internet of Vehicles, vehicle users face security threats such as eavesdropping, interference, and information tampering, which brings major challenges to the large-scale deployment of the Internet of Vehicles. The Internet of Vehicles usually uses encryption technology to encrypt the communication content, which ensures the security of the communication content and improves the securi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L29/06H04L29/08H04L9/06H04W4/40H04W12/0433
CPCH04L9/0631H04L63/06H04L67/12H04W4/40
Inventor 肖亮刘楚环肖奕霖徐堂炜
Owner XIAMEN UNIV