Revolutionizing Malware Detection With LLMs

View Sample PDF

Author(s): Attila Magyar (Capitol Technology University, USA)and Marwan Omar (Capitol Technology University, USA & Illinois Institute of Technology, USA)
Copyright: 2025
Pages: 26
Source title: Application of Large Language Models (LLMs) for Software Vulnerability Detection
Source Author(s)/Editor(s): Marwan Omar (Illinois Institute of Technology, USA)and Hewa Majeed Zangana (Duhok Polytechnic University, Iraq)
DOI: 10.4018/979-8-3693-9311-6.ch004

Keywords: Artificial Intelligence / Engineering Science Reference / Information Security & Privacy / Security & Forensics

Purchase

View Revolutionizing Malware Detection With LLMs on the publisher's website for pricing and purchasing information.

Abstract

Malware detection remains a critical challenge in cybersecurity, necessitating innovative approaches to identify and mitigate threats. Recent advancements in natural language processing (NLP) offer promising avenues for improving malware detection systems. This chapter explores the application of GPT-2, a state-of-the-art generative pre-trained transformer model, to enhance malware detection. The authors propose a novel methodology leveraging GPT-2's capabilities to analyze and classify opcode snippets and textual features associated with malware. The approach involves fine-tuning GPT-2 on a diverse dataset of malware and benign software to learn distinctive patterns and characteristics indicative of malicious behavior. The experimental results demonstrate that GPT-2 achieves significant improvements in detection accuracy and reduces false positives compared to traditional methods. This study highlights the potential of integrating advanced NLP models with cybersecurity practices, providing a robust framework for future research in malware detection.

The IRMA Community

Research IRM

Revolutionizing Malware Detection With LLMs

Purchase

Abstract

Related Content

IRMA Sponsors