A Hidden Markov Model-Based Intrusion Detection System for Internet of Vehicles

Abstract

The invention belongs to the field of intrusion detection algorithms in the Internet of Vehicles, in particular to an intrusion detection system for the Internet of Vehicles based on a hidden Markov model. The system is used for intrusion detection of False alert attack, Sybil attack, Black hole attack and DoS attack in the Internet of Vehicles. The system design mainly includes a pre-detection module, a DNN-based detection center module, an update module for recording vehicle status and generating a hidden Markov model, and a response center module for generating response signals. These modules together ensure the efficient operation of the Internet of Vehicles. In the state of attack detection, they complement each other and jointly complete an attack monitoring and defense process. Compared with the DNN-based IDS in terms of detection accuracy, overhead and detection time, the detection accuracy of the present invention is higher, and the average detection time is much shorter than the DNN-based IDS, and has less overhead at the same time. The present invention uses a pre-detection mechanism compared to The IDS used for state switching has less overhead and saves computing resources.

Description

technical field [0001] The invention belongs to the field of intrusion detection algorithms in the Internet of Vehicles, in particular to an intrusion detection system for the Internet of Vehicles based on a hidden Markov model. The system is used for intrusion detection of False alert attack, Sybil attack, Black hole attack and DoS attack in the Internet of Vehicles. Background technique [0002] As an important concept in the Internet of Things, the Internet of Vehicles has not only become a hot spot in academic research, but also has been widely used in the engineering field. Whether it is the Internet of Things or the Internet, the security issues behind it are the primary concerns, and these security issues are specifically manifested in severe traffic jams, increasing fuel consumption year by year, and a steady stream of traffic accidents. However, due to the rapid growth of the national economy year by year, the sales volume of automobiles has also doubled thereupon,...

AI Technical Summary

Problems solved by technology

The security problems in the computer network have long been exposed, and many problems have been effectively solved. However, due to the endless attacks in the Internet of Vehicles and the particularity of the field of the Internet of Vehicles, the same security problems not only behave differently in the Internet of Vehicles, and security solutions cannot be applied effectively

[0004] The Internet of Vehicles is a new generation of networks that are mainly data-centric, while some traditional networks are address-centric, so attacks that have little impact and damage on traditional networks will have a very large impact on the Internet of Vehicles. Hazardous

In addition, due to its dynamic topology, the Internet of Vehicles makes the security issues in the Internet of Vehicles more complicated, and the solution is no longer easy.

Images