Salvato in:
Dettagli Bibliografici
Autori principali: K, Ajvad Haneef, Singh, Karan Kuwar, D, Madhu Kumar S
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.23987
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917175492608000
author K, Ajvad Haneef
Singh, Karan Kuwar
D, Madhu Kumar S
author_facet K, Ajvad Haneef
Singh, Karan Kuwar
D, Madhu Kumar S
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23987
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MeLeMaD: Adaptive Malware Detection via Chunk-wise Feature Selection and Meta-Learning
K, Ajvad Haneef
Singh, Karan Kuwar
D, Madhu Kumar S
Cryptography and Security
Artificial Intelligence
Machine Learning
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.
title MeLeMaD: Adaptive Malware Detection via Chunk-wise Feature Selection and Meta-Learning
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.23987