Search:
Match:
1 results

Analysis

This paper introduces MeLeMaD, a novel framework for malware detection that combines meta-learning with a chunk-wise feature selection technique. The use of meta-learning allows the model to adapt to evolving threats, and the feature selection method addresses the challenges of large-scale, high-dimensional malware datasets. The paper's strength lies in its demonstrated performance on multiple datasets, outperforming state-of-the-art approaches. This is a significant contribution to the field of cybersecurity.
Reference

MeLeMaD outperforms state-of-the-art approaches, achieving accuracies of 98.04% on CIC-AndMal2020 and 99.97% on BODMAS.