What question did this study set out to answer?

The aim is to develop a robust hybrid neural network model that effectively detects malware by combining various advanced techniques.

A Deep Learning–Based Hybrid Neural Network Model for Malware Detection

View Full Paper

Ask AI

Bookmark

Authors

This research reveals a deep learning approach for malware detection, improving accuracy and addressing classification challenges.

The aim is to develop a robust hybrid neural network model that effectively detects malware by combining various advanced techniques.
Proposed a hybrid model incorporating CNN, RNNs, and attention mechanisms.
Used multi-scale convolutional layers and residual connections for improved generalization.
Implemented focal loss to handle class imbalance in malware datasets.
Evaluated the model on EMBER, EMBER Sim, and SoReL-20M datasets.
Achieved 96.7% accuracy and 96.1% precision in malware detection.
Demonstrated 96.8% recall and 96.4% F1-score, indicating high reliability.
Showed a 1.1–2.6% increment in accuracy compared to previous methods.
Excels in detecting zero-day exploits with minimal false positives.

Muthana S. Mahdi (2026) studied this question.

View Full Paper

Ask AI

Bookmark