Research Paper#Cybersecurity, Malware Detection, Meta-Learning, Feature Selection🔬 ResearchAnalyzed: Jan 3, 2026 16:52
MeLeMaD: Adaptive Malware Detection with Meta-Learning
Published:Dec 30, 2025 04:59
•1 min read
•ArXiv
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.
Key Takeaways
- •MeLeMaD is a novel framework for malware detection using meta-learning.
- •It incorporates Chunk-wise Feature Selection based on Gradient Boosting (CFSGB) for efficient handling of large datasets.
- •MeLeMaD outperforms state-of-the-art methods on multiple benchmark datasets.
- •The approach addresses the challenges of robustness, adaptability, and large-scale datasets in malware detection.
Reference
“MeLeMaD outperforms state-of-the-art approaches, achieving accuracies of 98.04% on CIC-AndMal2020 and 99.97% on BODMAS.”