Aug 2026· Scientific Reports· Vol 16· 0 citations· 68 references
Medicine
TL;DR
Evaluation using metrics such as accuracy, precision, F1 score, and false positive rate indicates that CNN-GBM outperforms existing deep learning models, and enhancements stem from the effective integration of CNN feature extraction with GBM’s boosting capabilities.
Abstract
Malware is malicious software that infiltrates systems without user consent. Effective detection involves identifying such software and distinguishing it from benign programs. While machine learning has shown promise in malware detection, many existing techniques demand extensive feature engineering and representation, leading to higher computation times and error rates. To address these limitations, we propose CNN-GBM, a hybrid model combining Convolutional neural networks (CNN) with Gradient Boosted Machines (GBM), aimed at improving Android malware detection. The approach begins by constructing a dataset comprising malware and benign files, represented as numerical feature vectors through n-grams, opcode sequences, or byte-level features. CNN processes the raw data to learn hierarchical patterns, while an entropy-based feature selection technique identifies the most informative attributes. These selected features are then fed into the GBM, trained to classify files as malware or benign. Evaluation using metrics such as accuracy, precision, F1 score, and false positive rate indicates that CNN-GBM outperforms existing deep learning models. Notable improvements include accuracy (+ 3%), precision (+ 1%), recall (+ 5%), AUC (+ 3.5%), and significant reductions in false positive rate (− 52%), false negative rate (− 15%), and error rate (− 35%). These enhancements stem from the effective integration of CNN feature extraction with GBM’s boosting capabilities.
The findings demonstrate the potential of using ensemble learning in conjunction with explainable artificial intelligence techniques to enhance malware detection systems and cybersecurity applications.
Haider Ali Muften· Journal for Technology and S...· 0 citations
A Hybrid Neural Network–Convolutional Neural Network (NN–CNN) Deep Learning Framework for malware detection, malware-family classification, and malware-variant identification and considers two important issues in practical malware detection: model explainability and generalization to previously unseen malware.
Chioma Grace Nwankwo, B. C. Amanze, Ikechukwu Amaefule· World Journal of Advanced Re...· 0 citations
Malicious Software (Malware) is an abusive term defined as malicious pieces of code or program scripts that can damage information technology systems. In 2025, malware remained one of the most critical cybersecurity threats, with over 6.5 billion attacks globally. There are almost 560,000 new malware samples daily and more than 75 percent of organizations experiencing ransomware attacks annually. AI driven attacks, cloud exploitation and mobile malware has significantly increased both the scale and sophistication of cyber threats. Classification of malware is very important in terms of ensuring the security of information systems. In literature, many studies have been done to classify malware so far. This study presents a convolutional neural network (CNN) architecture based on transfer learning using EfficientNetB4 for multi-class image classification. The model leverages pretrained weights from ImageNet and integrates a custom classification head. The proposed approach improves classification accuracy while reducing training time and overfitting compared to conventional CNN models trained from scratch.
Abdul Hanan, M. Rizwan, Sana Tariq et al.· ICACNC 2026 Proceedings· 0 citations
Malware severely threatens cybersecurity through Portable Executable (PE) files. In this study, the performances of machine learning and deep learning models for malware detection are compared using static analysis features extracted from PE files. Tree-based ensemble models like Random Forest, XGBoost, LightGBM, and CatBoost, along with MLP, DNN, and 1D-CNN deep learning architectures, were trained on a dataset comprising 62,485 samples and 15 features. Experimental results proved that ensemble algorithms outperform deep learning models on low-dimensional tabular data. Among the models, Random Forest achieved the highest success with 99.65% accuracy and a 99.59% F1-score. This academic study demonstrates that lightweight and high-performance tree-based models offer a more efficient solution for malware detection compared to computationally expensive deep neural networks.
Gokay Mutlu, Neşe Rihani, E. Bayazit· Signal Processing and Commun...· 0 citations
The rapid growth of Android applications has significantly increased the risk of malware attacks, making reliable malware detection an important cybersecurity challenge. Traditional detection methods often fail to identify newly emerging malware due to their dependence on predefined signatures and limited feature learning capabilities. This paper presents an intelligent Android malware detection framework that combines deep learning with the Equilibrium Optimizer to improve detection performance. Initially, Android application data are preprocessed to extract meaningful features for analysis. A Channel Attention Long ShortTerm Memory (CA-LSTM) model is employed to capture complex behavioral patterns and accurately distinguish malicious applications from benign ones. To further enhance the model's performance, the Equilibrium Optimizer is used to tune the hyperparameters, resulting in improved classification accuracy and faster convergence. Experimental evaluation on a benchmark Android malware dataset demonstrates that the proposed framework achieves superior detection performance compared with conventional machine learning methods, providing an effective and reliable solution for securing Android devices against evolving malware threats.
Aishwarya Eklar, G.Rajini· International Journal of Eng...· 0 citations
The rapid growth of Android applications has led to a significant increase in malware threats, making accurate and robust detection mechanisms essential for mobile security. However, challenges such as class imbalance and high-dimensional feature spaces limit the effectiveness of traditional machine learning approaches.
This work proposes a robust machine learning pipeline for accurate detection of Android malware by integrating generative data augmentation and deep feature extraction with classical classification models. We employ Conditional Tabular Generative Adversarial Networks (CTGAN) to synthetically balance a permission- and API-based feature dataset (TUANDROMD), developed at Tezpur University from real benign and malicious Android applications. An autoencoder is then utilized to learn compact and discriminative latent representations from the original 241 numerical features, effectively reducing dimensionality and redundancy. The extracted features are used to train multiple machine learning classifiers, including Logistic Regression, Random Forest, and XGBoost, enabling a comparative evaluation of model performance.
The models are assessed using accuracy, precision, recall, and F1-score under stratified validation and holdout testing. Four experimental configurations are investigated: (i) baseline classification using raw features, (ii) CTGAN-based data augmentation, (iii) autoencoder-based feature extraction, and (iv) CTGAN-based augmentation followed by autoencoder-driven feature extraction. Experimental results demonstrate that the combined CTGAN and autoencoder pipeline significantly improves minority-class detection while maintaining high overall accuracy. These findings highlight that integrating generative augmentation with learned feature representations is an effective strategy for handling high-dimensional, imbalanced Android malware datasets.
Shirina Samreen· Journal of engineering and a...· 0 citations