DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework

Abstract The existence of malicious software (malware) represents a potential threat to users who connect to a large set of services provided by multiple providers. Such malware is capable of stealing, spying on, encrypting data from users, and spreading, provoking impacts that are beyond a single c...

Full description

Saved in:
Bibliographic Details
Main Authors: Rodrigo Castillo Camargo, Juan Murcia Nieto, Nicolás Rojas, Daniel Díaz-López, Santiago Alférez, Angel Luis Perales Gómez, Pantaleone Nespoli, Félix Gómez Mármol, Umit Karabiyik
Format: Article
Language:English
Published: SpringerOpen 2025-04-01
Series:Cybersecurity
Subjects:
Online Access:https://doi.org/10.1186/s42400-025-00396-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314714687897600
author Rodrigo Castillo Camargo
Juan Murcia Nieto
Nicolás Rojas
Daniel Díaz-López
Santiago Alférez
Angel Luis Perales Gómez
Pantaleone Nespoli
Félix Gómez Mármol
Umit Karabiyik
author_facet Rodrigo Castillo Camargo
Juan Murcia Nieto
Nicolás Rojas
Daniel Díaz-López
Santiago Alférez
Angel Luis Perales Gómez
Pantaleone Nespoli
Félix Gómez Mármol
Umit Karabiyik
author_sort Rodrigo Castillo Camargo
collection DOAJ
description Abstract The existence of malicious software (malware) represents a potential threat to users who connect to a large set of services provided by multiple providers. Such malware is capable of stealing, spying on, encrypting data from users, and spreading, provoking impacts that are beyond a single citizen’s device and reaching critical information systems. To detect malware families, Machine Learning and Deep Learning techniques have been employed recently, demonstrating promising results. However, these techniques lack in detecting more advanced malware that employs obfuscation techniques. In this paper, we present DEFENDIFY, a novel framework, empowered by Computer Vision, Deep Learning, and Transfer Learning techniques, that is able to detect completely obfuscated malware with high performance in terms of accuracy and computational consumption. DEFENDIFY comprises three modules: Dataset Creation, Binary Obfuscation, and Model Generation. These modules work together to detect both obfuscated and non-obfuscated malware. The core module, i.e., the Model Generation, employs an entropy tester that determines whether a sample is obfuscated or not. Then, a Deep Learning model powered by Transfer Learning is employed to determine if it is malware or goodware. We validated our framework using real data gathered from malware repositories and legitimate software. The proposed framework was configured to test four Convolutional Neural Network architectures: ResNet18, ResNet34, EfficientNetB3, and EfficientNetV2S. Among them, the ResNet18 architecture obtained the best performance in detecting both non-obfuscated and obfuscated samples with an F1-score of 99.34% and 97.5%, respectively.
format Article
id doaj-art-80bce7a16a5d4a52b777b7eaf2a33c2a
institution Kabale University
issn 2523-3246
language English
publishDate 2025-04-01
publisher SpringerOpen
record_format Article
series Cybersecurity
spelling doaj-art-80bce7a16a5d4a52b777b7eaf2a33c2a2025-08-20T03:52:23ZengSpringerOpenCybersecurity2523-32462025-04-018112310.1186/s42400-025-00396-zDEFENDIFY: defense amplified with transfer learning for obfuscated malware frameworkRodrigo Castillo Camargo0Juan Murcia Nieto1Nicolás Rojas2Daniel Díaz-López3Santiago Alférez4Angel Luis Perales Gómez5Pantaleone Nespoli6Félix Gómez Mármol7Umit Karabiyik8School of Engineering, Science and Technology, Universidad del RosarioSchool of Engineering, Science and Technology, Universidad del RosarioSchool of Engineering, Pontifical Xavierian UniversitySchool of Engineering, Science and Technology, Universidad del RosarioDepartment of Mathematics, Barcelona East Engineering School, Polytechnic University of CataloniaFaculty of Computer Science, University of MurciaFaculty of Computer Science, University of MurciaFaculty of Computer Science, University of MurciaDepartment of Computer and Information Technology, Purdue UniversityAbstract The existence of malicious software (malware) represents a potential threat to users who connect to a large set of services provided by multiple providers. Such malware is capable of stealing, spying on, encrypting data from users, and spreading, provoking impacts that are beyond a single citizen’s device and reaching critical information systems. To detect malware families, Machine Learning and Deep Learning techniques have been employed recently, demonstrating promising results. However, these techniques lack in detecting more advanced malware that employs obfuscation techniques. In this paper, we present DEFENDIFY, a novel framework, empowered by Computer Vision, Deep Learning, and Transfer Learning techniques, that is able to detect completely obfuscated malware with high performance in terms of accuracy and computational consumption. DEFENDIFY comprises three modules: Dataset Creation, Binary Obfuscation, and Model Generation. These modules work together to detect both obfuscated and non-obfuscated malware. The core module, i.e., the Model Generation, employs an entropy tester that determines whether a sample is obfuscated or not. Then, a Deep Learning model powered by Transfer Learning is employed to determine if it is malware or goodware. We validated our framework using real data gathered from malware repositories and legitimate software. The proposed framework was configured to test four Convolutional Neural Network architectures: ResNet18, ResNet34, EfficientNetB3, and EfficientNetV2S. Among them, the ResNet18 architecture obtained the best performance in detecting both non-obfuscated and obfuscated samples with an F1-score of 99.34% and 97.5%, respectively.https://doi.org/10.1186/s42400-025-00396-zMalware detectionMalware obfuscationComputer visionTransfer learningDeep learningNetworking system of artificial intelligence
spellingShingle Rodrigo Castillo Camargo
Juan Murcia Nieto
Nicolás Rojas
Daniel Díaz-López
Santiago Alférez
Angel Luis Perales Gómez
Pantaleone Nespoli
Félix Gómez Mármol
Umit Karabiyik
DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework
Cybersecurity
Malware detection
Malware obfuscation
Computer vision
Transfer learning
Deep learning
Networking system of artificial intelligence
title DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework
title_full DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework
title_fullStr DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework
title_full_unstemmed DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework
title_short DEFENDIFY: defense amplified with transfer learning for obfuscated malware framework
title_sort defendify defense amplified with transfer learning for obfuscated malware framework
topic Malware detection
Malware obfuscation
Computer vision
Transfer learning
Deep learning
Networking system of artificial intelligence
url https://doi.org/10.1186/s42400-025-00396-z
work_keys_str_mv AT rodrigocastillocamargo defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT juanmurcianieto defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT nicolasrojas defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT danieldiazlopez defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT santiagoalferez defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT angelluisperalesgomez defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT pantaleonenespoli defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT felixgomezmarmol defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework
AT umitkarabiyik defendifydefenseamplifiedwithtransferlearningforobfuscatedmalwareframework