Deep Learning-Driven Malware Classification with API Call Sequence Analysis and Concept Drift Handling

TL;DR

This paper introduces a deep learning framework combined with genetic algorithms to improve malware classification accuracy and adaptability in dynamic environments with concept drift.

Contribution

It presents a novel hybrid approach that uses genetic algorithms to continuously refine deep learning models for malware detection amidst evolving threats.

Findings

Significantly improves classification accuracy over static models

Enhances model adaptability to concept drift

Outperforms traditional malware detection methods

Abstract

Malware classification in dynamic environments presents a significant challenge due to concept drift, where the statistical properties of malware data evolve over time, complicating detection efforts. To address this issue, we propose a deep learning framework enhanced with a genetic algorithm to improve malware classification accuracy and adaptability. Our approach incorporates mutation operations and fitness score evaluations within genetic algorithms to continuously refine the deep learning model, ensuring robustness against evolving malware threats. Experimental results demonstrate that this hybrid method significantly enhances classification performance and adaptability, outperforming traditional static models. Our proposed approach offers a promising solution for real-time malware classification in ever-changing cybersecurity landscapes.