An Intelligent Communication Warning Vulnerability Detection Algorithm Based on IoT Technology

Mao Yi, Xiaohui Xu, Lei Xu
2019 IEEE Access  
This paper mainly studies the vulnerability intelligent early warning technology in the IoT environment, and studies the network security assessment method based on the attack graph association analysis of the IoT environment, and analyzes the attack graph generation algorithm. Firstly, it uses the attack graph technology to establish a network security evaluation model based on the vulnerability association analysis in the IoT environment. The attack graph generation algorithm is improved. The
more » ... key attack path of the attack graph in the IoT environment is searched according to the node weight value. The key attack path of the network attack graph is used to measure the whole network security, and the security under the IoT environment is given. The measurement calculation model is used to realize the quantitative analysis of the security status of the IoT environment by using the attack graph. Secondly, an intelligent early warning vulnerability detection algorithm based on the dynamic stain propagation model in the IoT environment is proposed, focusing on the introduction of stains and the inspection of stains. A static detection method for early warning vulnerabilities based on the counter-example of the IoT is proposed. Through the flow detection and context sensitive detection, a possible buffer early warning vulnerability is discovered. The driver crawler realizes automatic detection, and uses function hijacking to detect the execution of the stain data. In the experimental environment, compared with the existing tools, the experimental data shows that the algorithm improves the accuracy, recall rate and efficiency of the unfiltered vulnerability of intelligent early warning detection, and proves that the proposed algorithm can effectively detect the vulnerability. INDEX TERMS Security measurement calculation model, IoT, intelligent early warning, vulnerability mining detection.
doi:10.1109/access.2019.2953075 fatcat:3orqu5nisjhudhjtrmzmeig36q