A malware detection method with function parameters encoding and function dependency modeling

As computers are widely used in people’s work and daily lives, malware has become an increasing threat to network security. Although researchers have introduced traditional machine learning and deep learning methods to conduct extensive research on functions in malware detection, these methods have...

Full description

Saved in:
Bibliographic Details
Main Authors: Ronghao Hou, Dongjie Liu, Xiaobo Jin, Jian Weng, Guanggang Geng
Format: Article
Language:English
Published: PeerJ Inc. 2025-06-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2946.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849693980703326208
author Ronghao Hou
Dongjie Liu
Xiaobo Jin
Jian Weng
Guanggang Geng
author_facet Ronghao Hou
Dongjie Liu
Xiaobo Jin
Jian Weng
Guanggang Geng
author_sort Ronghao Hou
collection DOAJ
description As computers are widely used in people’s work and daily lives, malware has become an increasing threat to network security. Although researchers have introduced traditional machine learning and deep learning methods to conduct extensive research on functions in malware detection, these methods have largely ignored the analysis of function parameters and functional dependencies. To address these limitations, we propose a new malware detection method. Specifically, we first design a parameter encoder to convert various types of function parameters into feature vectors, and then discretize various parameter features through clustering methods to enhance the representation of API encoding. Additionally, we design a deep neural network to capture functional dependencies, enabling the generation of robust semantic representations of function sequences. Experiments on a large-scale malware detection dataset demonstrate that our method outperforms other techniques, achieving 98.62% accuracy and a 98.40% F1-score. Furthermore, the results of ablation experiments show the important role of function parameters and functional dependencies in malware detection.
format Article
id doaj-art-3fa589c77822484e94c5ca2a67235692
institution DOAJ
issn 2376-5992
language English
publishDate 2025-06-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-3fa589c77822484e94c5ca2a672356922025-08-20T03:20:14ZengPeerJ Inc.PeerJ Computer Science2376-59922025-06-0111e294610.7717/peerj-cs.2946A malware detection method with function parameters encoding and function dependency modelingRonghao Hou0Dongjie Liu1Xiaobo Jin2Jian Weng3Guanggang Geng4School for Cyberspace Security, Jinan University, Guangzhou, Guangdong, ChinaSchool for Cyberspace Security, Jinan University, Guangzhou, Guangdong, ChinaDepartment of Electrical and Electronic Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, Jiangsu, ChinaSchool for Cyberspace Security, Jinan University, Guangzhou, Guangdong, ChinaSchool for Cyberspace Security, Jinan University, Guangzhou, Guangdong, ChinaAs computers are widely used in people’s work and daily lives, malware has become an increasing threat to network security. Although researchers have introduced traditional machine learning and deep learning methods to conduct extensive research on functions in malware detection, these methods have largely ignored the analysis of function parameters and functional dependencies. To address these limitations, we propose a new malware detection method. Specifically, we first design a parameter encoder to convert various types of function parameters into feature vectors, and then discretize various parameter features through clustering methods to enhance the representation of API encoding. Additionally, we design a deep neural network to capture functional dependencies, enabling the generation of robust semantic representations of function sequences. Experiments on a large-scale malware detection dataset demonstrate that our method outperforms other techniques, achieving 98.62% accuracy and a 98.40% F1-score. Furthermore, the results of ablation experiments show the important role of function parameters and functional dependencies in malware detection.https://peerj.com/articles/cs-2946.pdfMalware detectionAPI sequenceDeep learningRun-time parameter
spellingShingle Ronghao Hou
Dongjie Liu
Xiaobo Jin
Jian Weng
Guanggang Geng
A malware detection method with function parameters encoding and function dependency modeling
PeerJ Computer Science
Malware detection
API sequence
Deep learning
Run-time parameter
title A malware detection method with function parameters encoding and function dependency modeling
title_full A malware detection method with function parameters encoding and function dependency modeling
title_fullStr A malware detection method with function parameters encoding and function dependency modeling
title_full_unstemmed A malware detection method with function parameters encoding and function dependency modeling
title_short A malware detection method with function parameters encoding and function dependency modeling
title_sort malware detection method with function parameters encoding and function dependency modeling
topic Malware detection
API sequence
Deep learning
Run-time parameter
url https://peerj.com/articles/cs-2946.pdf
work_keys_str_mv AT ronghaohou amalwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT dongjieliu amalwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT xiaobojin amalwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT jianweng amalwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT guangganggeng amalwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT ronghaohou malwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT dongjieliu malwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT xiaobojin malwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT jianweng malwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling
AT guangganggeng malwaredetectionmethodwithfunctionparametersencodingandfunctiondependencymodeling