MeLeMaD: Adaptive Malware Detection via Chunk-wise Feature Selection and Meta-Learning

TL;DR

MeLeMaD introduces a meta-learning framework with a novel feature selection method to improve malware detection accuracy and efficiency across diverse datasets, addressing robustness and adaptability challenges.

Contribution

The paper presents a new malware detection framework combining model-agnostic meta-learning with chunk-wise feature selection for enhanced adaptability and performance.

Findings

Achieved over 98% accuracy on benchmark datasets.

Outperformed existing methods in precision, recall, and F1-score.

Demonstrated robustness and scalability on large, high-dimensional datasets.

Abstract

Confronting the substantial challenges of malware detection in cybersecurity necessitates solutions that are both robust and adaptable to the ever-evolving threat environment. The paper introduces Meta Learning Malware Detection (MeLeMaD), a novel framework leveraging the adaptability and generalization capabilities of Model-Agnostic Meta-Learning (MAML) for malware detection. MeLeMaD incorporates a novel feature selection technique, Chunk-wise Feature Selection based on Gradient Boosting (CFSGB), tailored for handling large-scale, high-dimensional malware datasets, significantly enhancing the detection efficiency. Two benchmark malware datasets (CIC-AndMal2020 and BODMAS) and a custom dataset (EMBOD) were used for rigorously validating the MeLeMaD, achieving a remarkable performance in terms of key evaluation measures, including accuracy, precision, recall, F1-score, MCC, and AUC. With accuracies of 98.04\% on CIC-AndMal2020 and 99.97\% on BODMAS, MeLeMaD outperforms the state-of-the-art approaches. The custom dataset, EMBOD, also achieves a commendable accuracy of 97.85\%. The results underscore the MeLeMaD's potential to address the challenges of robustness, adaptability, and large-scale, high-dimensional datasets in malware detection, paving the way for more effective and efficient cybersecurity solutions.