RealMalSol: real-time optimized model for Android malware detection using efficient neural networks and model quantization

Chaudhary, Maham; Masood, Ammar

doi:10.1007/s00521-023-08303-8

Cited by 12 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highest results achieved by the PreLU method were 99.01% accuracy, 99.4% recall, 99.3% F1-score and precision, and 0.986 AUC-ROC. Another study used static analysis to detect Android malware and considered it as a first-line defense, as malware could be detected upon installation [22]. The CICInvesandMal2019 dataset was used to analyze malware detection, while efficient feature reduction was applied to reduce the feature set.…”

Section: Related Workmentioning

confidence: 99%

A Novel Neural Network Architecture Using Automated Correlated Feature Layer to Detect Android Malware Applications

Alabrah

2023

Mathematics

View full text Add to dashboard Cite

Android OS devices are the most widely used mobile devices globally. The open-source nature and less restricted nature of the Android application store welcome malicious apps, which present risks for such devices. It is found in the security department report that static features such as Android permissions, manifest files, and API calls could significantly reduce malware app attacks on Android devices. Therefore, an automated method for malware detection should be installed on Android devices to detect malicious apps. These automated malware detection methods are developed using machine learning methods. Previously, many studies on Android OS malware detection using different feature selection approaches have been proposed, indicating that feature selection is a widely used concept in Android malware detection. The feature dependency and the correlation of the features enable the malicious behavior of an app to be detected. However, more robust feature selection using automated methods is still needed to improve Android malware detection methods. Therefore, this study proposed an automated ANN-method-based Android malware detection method. To validate the proposed method, two public datasets were used in this study, namely the CICInvestAndMal2019 and Drebin/AMD datasets. Both datasets were preprocessed via their static features to normalize the features as binary values. Binary values indicate that certain permissions in any app are enabled (1) or disabled (0). The transformed feature sets were given to the ANN classifier, and two main experiments were conducted. In Experiment 1, the ANN classifier used a simple input layer, whereas a five-fold cross-validation method was applied for validation. In Experiment 2, the proposed ANN classifier used a proposed feature selection layer. It includes selected features only based on correlation or dependency with respect to benign or malware apps. The proposed ANN-method-based results are significant, improved, and robust and were better than those presented in previous studies. The overall results of using the five-fold method on the CICInvestAndMal2019 dataset were a 95.30% accuracy, 96% precision, 98% precision, and 92% F1-score. Likewise, on the AMD/Drebin dataset, the overall scores were a 99.60% accuracy, 100% precision and recall, and 99% F1-score. Furthermore, the computational cost of both experiments was calculated to prove the performance improvement brought about by the proposed ANN classifier compared to the simple ANN method with the same time of training and prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Neural Network Architecture Using Automated Correlated Feature Layer to Detect Android Malware Applications

Alabrah

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Thereby, alarmingly enhancing the rate of malicious applications and their difficulties has become a serious challenge. Every ten seconds, recent reports represent that at least one malware is declared in every app store [4,5]. This has led to escalating malware attacks between Android devices/applications and OS.…”

Section: Introductionmentioning

confidence: 99%

Feature Selection Using Adaptive Weight Based Grey Wolf Optimization for Malware Detection in Android

2024

IJIES

View full text Add to dashboard Cite

The malware application is one of the most dangerous threats to various applications, particularly in Android devices. To effectively detect the malware in Android, the existing researchers utilized the Machine Learning (ML) approaches. However, the researchers have not accurately detected the malware due to the malware complexity, continuous changes as well as increased damages caused by attackers. In this paper, an Adaptive Weight based Grey Wolf Optimization (AWGWO) based feature selection is proposed for malware detection in Android. The proposed AWGWO is evaluated by using Drebin and CICInvesAndMal2019 dataset which contains 216 and 428 malware features. Then, the acquired dataset is pre-processed by utilizing the Min-Max normalization technique to remove the computational complexity and achieve minimum error rates. In the classification stage, a voting combination of benign and malignant malware is used while utilizing three ensemble ML approaches. The ensemble approaches involve a Support Vector Machine (SVM), Random Forest (RF) and AdaBoost algorithm. The proposed AWGWO method achieves better results by using evaluation metrics like accuracy, precision, recall, and F1-score of 0.9953, 0.9930, 0.9963, and 0.9725 respectively which is comparatively better than the existing methods named Random Forest-OWL (RF-OWL), SVM, Adjacency Matrix (AdMat) and Effective Feature selection -RF (EF-RF).

show abstract

IPAnalyzer: A novel Android malware detection system using ranked Intents and Permissions

Sharma,

Arora

2024

Multimed Tools Appl

View full text Add to dashboard Cite

RealMalSol: real-time optimized model for Android malware detection using efficient neural networks and model quantization

Cited by 12 publications

References 48 publications

A Novel Neural Network Architecture Using Automated Correlated Feature Layer to Detect Android Malware Applications

A Novel Neural Network Architecture Using Automated Correlated Feature Layer to Detect Android Malware Applications

Feature Selection Using Adaptive Weight Based Grey Wolf Optimization for Malware Detection in Android

IPAnalyzer: A novel Android malware detection system using ranked Intents and Permissions

Contact Info

Product

Resources

About