Process detection method and system for application program

Abstract

The embodiment of the invention provides a process detection method and system for an application program, and the method comprises the steps: obtaining an observable behavior vector corresponding tothe process according to the content of a safety log; converting the observable behavior vector into a process behavior feature map; and detecting the process behavior feature map based on a trained convolutional neural network model to obtain a detection result of the process, wherein the trained convolutional neural network model is obtained by training a sample process behavior characteristic graph marked with a normal process label and a process behavior characteristic graph marked with a malicious process label. The abnormal process can be effectively identified, the defect of low accuracy of identifying the abnormal process through a manual technology in the prior art is overcome, and the method has good adaptability and relatively high robustness for different types of malicious processes.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a process detection method and system for application programs. Background technique [0002] In recent years, the number of malicious programs has grown exponentially, and has become one of the key factors threatening Internet security. How to effectively detect and kill malicious programs has also become one of the most important issues for enterprises and network security personnel. With the continuous development and improvement of artificial intelligence technology, how to apply artificial intelligence technology to malicious program detection and realize self-inspection in unsupervised or semi-supervised mode of the system has become one of the needs of current enterprises. [0003] For the detection and killing of malicious programs, most current technologies analyze the source code of malicious programs, extract corresponding features, and then scan and kill malicious ...

AI Technical Summary

Problems solved by technology

Among them, there are a large number of variants of some malicious programs and malicious program source codes, and the existing malicious program source code detection technology cannot effectively detect them.

Images