Toward a Taxonomy and Multi-label Dataset for Malware Classification

Rolando Sanchez-Fraga, Raul Acosta-Bermejo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The amount of malicious software detected in the wild have greatly increased over the years, same as their complexity and ability to avoid detection mechanisms and techniques improved. To aid in identifying and defending against this malware, we propose a multi-dimensional and multi-level malware taxonomy, a multi-label classification scheme, a multi-label malware dataset and a tool to automate the process of analyzing, labeling, preprocessing and presentation. Alongside this, we discuss the current state of each element and future work.

Original languageEnglish
Title of host publicationProceedings - 2022 10th International Conference in Software Engineering Research and Innovation, CONISOFT 2022
EditorsReyes Juarez-Ramirez, Carlos Alberto Fernandez y Fernandez, Hector G. Perez-Gonzalez, Hector G. Perez-Gonzalez, Alan Ramirez-Noriega, Samantha Paulina Jimenez Calleros, Cesar Arturo Guerra-Garcia, Guillermo Licea Sandoval
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages150-157
Number of pages8
ISBN (Electronic)9781665461269
DOIs
StatePublished - 2022
Event10th International Conference in Software Engineering Research and Innovation, CONISOFT 2022 - Ciudad Modelo, San Jose Chiapa, Mexico
Duration: 24 Oct 202228 Oct 2022

Publication series

NameProceedings - 2022 10th International Conference in Software Engineering Research and Innovation, CONISOFT 2022

Conference

Conference10th International Conference in Software Engineering Research and Innovation, CONISOFT 2022
Country/TerritoryMexico
CityCiudad Modelo, San Jose Chiapa
Period24/10/2228/10/22

Keywords

  • malware analysis
  • malware classification
  • malware dataset
  • malware taxonomy
  • multi-label classification

Fingerprint

Dive into the research topics of 'Toward a Taxonomy and Multi-label Dataset for Malware Classification'. Together they form a unique fingerprint.

Cite this