Methods for detecting malware

By converting computer files into image data and using machine learning methods for static analysis, the problems of low malware detection efficiency and poor adaptability in existing technologies are solved, and efficient and robust detection of different file types and sizes is achieved.

CN116368487BActive Publication Date: 2025-09-16INLISER CO LTD
1 Cites 0 Cited by

Patent Information

Application Number
CN202080106696.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-10-30
Publication Date
2025-09-16
Estimated Expiration
2040-10-30

AI Technical Summary

Technical Problem

Existing malware detection methods struggle to maintain high security and efficiency when faced with computer files of varying types and sizes. Static analysis methods' signature matching struggles to keep up with the rapid evolution of malware, while dynamic analysis methods are computationally intensive and costly.

Method used

Convert computer files into multiple different image data, use machine learning, especially deep learning methods, to classify the image data, detect malware through static analysis, and use image classification modules and classifier modules to evaluate the presence of malware.

Benefits of technology

It achieves efficient and robust malware detection for computer files of different types and sizes, avoids the risks that may be brought by dynamic execution, improves the detection success rate and enhances resistance to obfuscation techniques.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

In order to improve the efficiency of malware detection, a method is proposed that can process computer files (1) of different types and sizes while maintaining high detection performance by classifying a plurality of images (4) of different types (A, B, C, D, E), each of which is calculated or derived from a specific computer file under test (1) (CFUT) using an artificial intelligence method, such as machine learning, in particular deep learning, for example provided by a neural network (24) or a supervised deep learning algorithm. Different image transformation techniques are used to generate the different image types (A, B, C, D, E), and a plurality of methods are proposed to calculate an image (4) of uniform size Si containing relevant information for classifying the CFUT (1).
Need to check novelty before this filing date? Find Prior Art