Dynamic Malware Detection Using LSTM Based GANs and Linux System Calls

Jeffrey C. Rombough, Larbi Esmahi

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

Abstract

Malware developers have learned how to confuse researchers who are trying to reverse engineer their methods in static analysis. Dynamic analysis monitors the computer’s behaviour during malware execution and has an advantage over static analysis as it is less susceptible to malware’s attempts of method obfuscation. With the widespread use of Linux-based Internet of Things (IoT) devices, attacks on Linux-based assets have significantly increased. Linux uses system calls to allow a user’s program to interface with the operating system’s resources. These system calls can be analyzed in a dynamic fashion to determine if malware is affecting the operating system’s behaviour. In this paper, the combination of two AI technologies, Generative Adversarial Network (GAN) and Long-Short-Term-Memory (LSTM) network are used for detecting malware in Linux systems. The experimental findings of this research show promising results for using such technology in malware detection.

Original languageEnglish
Title of host publicationComputational Science and Computational Intelligence - 11th International Conference, CSCI 2024, Proceedings
EditorsHamid R. Arabnia, Leonidas Deligiannidis, Farzan Shenavarmasouleh, Soheyla Amirian, Farid Ghareh Mohammadi
Pages77-90
Number of pages14
DOIs
Publication statusPublished - 2025
Event11th International Conference on Computational Science and Computational Intelligence, CSCI 2024 - Las Vegas, United States
Duration: 11 Dec. 202413 Dec. 2024

Publication series

NameCommunications in Computer and Information Science
Volume2510 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference11th International Conference on Computational Science and Computational Intelligence, CSCI 2024
Country/TerritoryUnited States
CityLas Vegas
Period11/12/2413/12/24

Keywords

  • Generative Adversarial Network
  • Linux system calls
  • LSTM
  • Machine learning
  • Malware detection

Fingerprint

Dive into the research topics of 'Dynamic Malware Detection Using LSTM Based GANs and Linux System Calls'. Together they form a unique fingerprint.

Cite this