Article
Computer Science, Theory & Methods
Syed Ibrahim Imtiaz, Saif ur Rehman, Abdul Rehman Javed, Zunera Jalil, Xuan Liu, Waleed S. Alnumay
Summary: As the use of Android smartphones becomes more widespread, there is an increasing need for more efficient methods to detect and prevent malicious applications from attacking and compromising user devices.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Engineering, Multidisciplinary
Huijuan Zhu, Yang Li, Ruidong Li, Jianqiang Li, Zhuhong You, Houbing Song
Summary: The study introduces a stacking ensemble framework SEDMDroid to identify Android malware, utilizing techniques such as random feature subspaces and bootstrapping samples to ensure diversity, and employing Principal Component Analysis and Support Vector Machine for accuracy. Experimental results on two datasets demonstrate high accuracy rates, indicating the proposed method is effective for identifying Android malware.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Alejandro Guerra-Manzanares, Marcin Luckner, Hayretdin Bahsi
Summary: The study presents a novel method to detect and address concept drift in Android malware detection, maintaining high performance over an extended period and minimizing the need for model retraining efforts.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Francesco Mercaldo, Giovanni Ciaramella, Giacomo Iadarola, Marco Storto, Fabio Martinelli, Antonella Santone
Summary: With the rapid growth of the mobile device market, mobile malware has become increasingly sophisticated. Researchers have focused on developing malware detection systems to enhance the security of sensitive information. In this study, five state-of-the-art Convolutional Neural Network models, one author-developed network, and two quantum models were compared to classify malware. The models achieved the best performance in Android malware detection, and the predictions were explained using the Gradient-weighted Class Activation Mapping.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Hui-juan Zhu, Wei Gu, Liang-min Wang, Zhi-cheng Xu, Victor S. Sheng
Summary: The popularity and flexibility of the Android platform make it a prime target for malicious attackers. By extracting permissions, API calls, and hardware features, a new malware detection framework called MSerNetDroid is proposed. The framework utilizes a novel architectural unit, Multi-Head Squeeze-and-Excitation Residual block (MSer), to learn the correlation between features and recalibrate them from multiple perspectives. Experimental results show that MSerNetDroid successfully detects malware with an accuracy of 96.48%, outperforming state-of-the-art approaches.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Junyang Qiu, Jun Zhang, Wei Luo, Lei Pan, Surya Nepal, Yang Xiang
Summary: Deep Learning (DL) is a disruptive technology that has revolutionized cyber security research, especially in the detection and classification of Android malware. While offering many advantages, DL faces challenges such as choice of architecture, feature extraction, and obtaining high-quality data.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Artificial Intelligence
Hui-juan Zhu, Yang Li, Liang-min Wang, Victor S. Sheng
Summary: The continuous malware attacks on smartphones, especially on the dominant platform Android, pose a serious security threat to users. Data-driven methods based on machine learning algorithms show promise in defending against these attacks. This paper explores the limitations of such methods in improving malware detection performance and proposes a multi-model ensemble framework called MEFDroid, which combines individual predictors and utilizes hybrid deep learning based feature extraction methods to learn meaningful features from raw data.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sohail Khan, Mohammad Nauman, Suleiman Ali Alsaif, Toqeer Ali Syed, Hassan Ahmad Eleraky
Summary: Mobile phones are essential in modern life, and the Android and iOS platforms have a significant impact. Android currently dominates the market with over 84% share, but it also faces the challenge of malware. To tackle this, researchers have used deep learning models, but understanding the features extracted by these models in the malware domain is difficult. To address this issue, Capsule Networks (CapsNets), a state-of-the-art deep learning model, is proposed to capture spatial relationships in malware analysis.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
Alfonso Gomez, Antonio Munoz
Summary: The proliferation of Android-based devices has made them a prime target for attackers. This study presents a supervised learning technique that demonstrates promising results in Android malware detection.
Article
Chemistry, Analytical
Hasan Alkahtani, Theyazn H. H. Aldhyani
Summary: With the rapid expansion of smartphone usage, malicious attacks against Android mobile devices are increasing. This study successfully detected malware in Android applications using machine learning and deep learning approaches, and demonstrated their efficiency compared to existing security systems.
Article
Multidisciplinary Sciences
Wael F. Elsersy, Nor Badrul Anuar, Mohd Faizal Ab Razak
Summary: This study proposes a framework for detecting Android rooted devices using machine learning classification techniques, and the experimental evaluation shows a high level of accuracy for the framework.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Software Engineering
Lwin Khin Shar, Biniam Fisseha Demissie, Mariano Ceccato, Yan Naing Tun, David Lo, Lingxiao Jiang, Christoph Bienert
Summary: Android malware detection is an active research field, with machine learning-based approaches proposed using different features such as API usage and sequences. The study found that permission use features performed the best, package-level features were generally better than class-level features, and static features generally outperformed dynamic features.
EMPIRICAL SOFTWARE ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Shivi Garg, Niyati Baliyan
Summary: The paper introduces a DL framework 'M2VMapper' that uses transfer learning and pretrained language models to map malware and potential vulnerabilities. The study demonstrates that the framework delivers highly promising results in measuring the severity of vulnerabilities and malware.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Huanran Wang, Weizhe Zhang, Hui He
Summary: The use of Android devices has increased significantly in recent years, but the availability of third-party channels for downloading apps has created opportunities for malware. To address this issue, a hybrid Android malware detection approach combining dynamic and static strategies is proposed. Experimental results demonstrate high accuracy in malware detection.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Mulhem Ibrahim, Bayan Issa, Muhammed Basheer Jasser
Summary: Android is dominating the global smartphone market, leading to a strong need for effective security measures. This research proposes a new method for detecting and classifying Android malware using deep learning models and static analysis, achieving high accuracy in malware detection and classification.