An Efficient DenseNet-Based Deep Learning Model for Malware Detection

Abstract

Recently, there has been a huge rise in malware growth, which creates a significant security threat to organizations and individuals. Despite the incessant efforts of cybersecurity research to defend against malware threats, malware developers discover new ways to evade these defense techniques. Traditional static and dynamic analysis methods are ineffective in identifying new malware and pose high overhead in terms of memory and time. Typical machine learning approaches that train a classifier based on handcrafted features are also not sufficiently potent against these evasive techniques and require more efforts due to feature-engineering. Recent malware detectors indicate performance degradation due to class imbalance in malware datasets. To resolve these challenges, this work adopts a visualization-based method, where malware binaries are depicted as two-dimensional images and classified by a deep learning model. We propose an efficient malware detection system based on deep learning. The system uses a reweighted class-balanced loss function in the final classification layer of the DenseNet model to achieve significant performance improvements in classifying malware by handling imbalanced data issues. Comprehensive experiments performed on four benchmark malware datasets show that the proposed approach can detect new malware samples with higher accuracy (98.23% for the Malimg dataset, 98.46% for the BIG 2015 dataset, 98.21% for the MaleVis dataset, and 89.48% for the unseen Malicia dataset) and reduced false-positive rates when compared with conventional malware mitigation techniques while maintaining low computational time. The proposed malware detection solution is also reliable and effective against obfuscation attacks.

Analysis of Autoencoders for Network Intrusion Detection

“…Specifically, the authors compared the effectiveness of ensemble machine-learning approaches under several different settings: an ensemble of either homogeneous or heterogeneous classification models. Hemalatha et al [ 31 ] proposed a malware detection method based on deep learning. This method transforms program binary files into two-dimensional images and used a pretrained deep-learning model called DenseNet to classify the binary images.…”

Machine-Learning-Enabled Intrusion Detection System for Cellular Connected UAV Networks

“…The authors used 1551 malicious PHP webshells and 2593 normal PHP scripts for IoT security testing. The authors of [51] used DenseNetbased deep learning model to classify malware by handling imbalanced data issues. This model was evaluated on four malware datasets and can detect malwares move efficiently than conventional malware detection.…”

Multivariable Heuristic Approach to Intrusion Detection in Network Environments

“…By defining the probability of an event, it can be determined whether the event is recurring or rare. With regard to a computer network, the entropy of a phenomenon can determine whether it is a desired activity in a given network or an anomaly [ 55 , 56 ].…”