Research Article
Design of Adaptive Detection Algorithm for Mobile Social Network Security Vulnerability Based on Static Analysis
@INPROCEEDINGS{10.1007/978-3-031-50546-1_26, author={Fang Qian and Qiang Chen and Lincheng Li}, title={Design of Adaptive Detection Algorithm for Mobile Social Network Security Vulnerability Based on Static Analysis}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part II}, proceedings_a={ADHIP PART 2}, year={2024}, month={3}, keywords={Static Analysis Mobile Social Network Loophole Adaptive Testing}, doi={10.1007/978-3-031-50546-1_26} }- Fang Qian
Qiang Chen
Lincheng Li
Year: 2024
Design of Adaptive Detection Algorithm for Mobile Social Network Security Vulnerability Based on Static Analysis
ADHIP PART 2
Springer
DOI: 10.1007/978-3-031-50546-1_26
Abstract
In order to improve the accuracy of adaptive detection of security vulnerabilities in mobile social networks and achieve the ideal effect of high-precision adaptive detection of vulnerabilities, static analysis is introduced and an adaptive detection algorithm design of security vulnerabilities in mobile social networks based on static analysis is developed. Use plug-in technology to scan mobile social network ports, databases, operating systems, Web, security baselines, weak passwords, and industrial control systems to obtain network data. The abnormal data propagation rules are used to preprocess the scanned data and extract the network abnormal data. The static analysis of the extracted abnormal data defines the corresponding rules of network security vulnerabilities by building an abstract simulation of network applications, extracts the corresponding relationship between abnormal data and network security vulnerabilities, calculates the final score of network security vulnerabilities according to the basic evaluation utilization factor, and identifies and detects the security vulnerabilities of mobile social networks. The experimental analysis results show that the designed algorithm has a vulnerability detection rate of more than 90% with and without security protection mechanism, and the adaptive vulnerability detection rate is high.
