Vulnerability detection method and system based on attack surface

Abstract

The invention provides a vulnerability detection method and system based on an attack surface. By modifying an existing attack surface analysis method, integrating flows of different network slices, extracting a multi-dimensional feature set according to identification information, sending the multi-dimensional feature set to a machine learning model for detection and performing targeted tracing according to the type of an abnormal feature set, the problem of network slicing in existing attack surface analysis is solved; and vulnerability points are obtained through tracing, and morphologicalanalysis of transformation is performed on vulnerability infection surfaces, so that defense strategies can be dynamically deployed on key nodes, and the problem that the morphological analysis of vulnerabilities is different from the morphological analysis of network attacks is solved.

Description

technical field [0001] The present application relates to the technical field of network security, and in particular, to a method and system for vulnerability detection based on an attack surface. Background technique [0002] With the rapid development of network technology, security vulnerabilities emerge in an endless stream, and more and more network nodes make the detection of vulnerabilities more and more difficult, and it is even more difficult to trace the development of vulnerabilities according to the conventional propagation path. . [0003] The existing attack surface analysis methods can solve the problems of concealment, fragmentation and correlation to a certain extent, but there are still problems such as network slicing, and the morphological analysis of vulnerabilities is different from the morphological analysis of network attacks. There is an urgent need for a targeted attack surface-based vulnerability detection method and system. SUMMARY OF THE INVEN...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method and system for vulnerability detection based on the attack surface. By transforming the existing attack surface analysis method, the traffic of different network slices is integrated, and the multi-dimensional feature set is extracted according to the identification information, and sent to the machine learning model for detection. , and according to the type of abnormal feature set, targeted traceability can solve the problem of network slicing in the existing attack surface analysis; the vulnerability point is obtained through traceability, and the morphological analysis of the modification of the vulnerability infection surface can be realized. Deploy defense strategies to solve the problem that the morphological analysis of vulnerabilities is different from the morphological analysis of network attacks

Images