Article
Computer Science, Artificial Intelligence
Altyeb Altaher Taha, Sharaf Jameel Malebary
Summary: The proposed hybrid approach integrating FCM algorithm and LightGBM improves the classification efficiency of Android malicious apps by utilizing fuzzy clustering and machine learning techniques, achieving higher accuracy and learning efficiency.
NEURAL COMPUTING & APPLICATIONS
(2021)
Review
Computer Science, Information Systems
Asma Razgallah, Raphael Khoury, Sylvain Halle, Kobra Khanmohammadi
Summary: This paper investigates the main mechanisms and approaches for malware detection in Android applications, identifying the advantages and limitations of each, and suggesting avenues for future research in this area.
COMPUTER SCIENCE REVIEW
(2021)
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
Junwei Tang, Ruixuan Li, Yu Jiang, Xiwu Gu, Yuhua Li
Summary: Android malware poses a serious security threat, and obfuscation technology can generate variants that bypass existing detection methods. The proposed MGOPDroid system combines opcode feature extraction, TFIDF algorithm, and deep learning detection model for efficient anti-obfuscation Android malware detection. Experimental results show that the detection accuracy for both unobfuscated and obfuscated malware samples is over 90% with MGOPDroid.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Software Engineering
Matin Katebi, Afshin RezaKhani, Saba Joudaki, Mohammad Ebrahim Shiri
Summary: This article proposes RAPSAMS, a method that extends affinity propagation clustering to robustly cluster malware streams. The approach uses AP for clustering samples and introduces adversarial examples to attack the clustering algorithm and create a robust defense. The proposed method addresses the challenges of finding appropriate representations for clustering and managing patterns with different distributions. Experimental results demonstrate the adaptability and effectiveness of the proposed methods. AP clustering is shown to be robust against label flipping attacks.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Geosciences, Multidisciplinary
Ruhhee Tabbussum, Abdul Qayoom Dar
Summary: This research explores the capability of the adaptive neuro-fuzzy inference algorithm architecture to simulate floods, using multiple statistical performance evaluators to assess the established models and evaluating their validity and predictive power through flood occurrence prediction. The best performability was found in an ANFIS model created with a hybrid training algorithm, indicating the potential use of the model for flood prediction.
Article
Computer Science, Information Systems
Alejandro Guerra-Manzanares, Hayretdin Bahsi, Sven Nomm
Summary: This study discusses the evolution of Android malware datasets, the impact of time variables, the significance of data sources, and key factors in building more effective, robust, and long-lasting Android malware detection systems.
COMPUTERS & SECURITY
(2021)
Review
Computer Science, Information Systems
Shivi Garg, Niyati Baliyan
Summary: This paper provides a comparative analysis of Android and iOS in terms of security aspects, revealing that Android is more susceptible to security breaches and malware attacks compared to iOS. Therefore, researchers should focus on solving security issues related to Android to provide a safer mobile operating system for users.
COMPUTER SCIENCE REVIEW
(2021)
Review
Computer Science, Theory & Methods
Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu
Summary: Malicious applications, especially those targeting Android, pose a serious threat to developers and end-users. Existing defense approaches based on manual rules or traditional machine learning may not be effective due to the rapid growth of Android malware and the advancement of evasion technologies. Deep learning (DL) techniques have shown promising performance in various domains, so applying DL to Android malware defenses has gained significant research attention. This article presents a systematic literature review that identifies 132 studies from 2014 to 2021, revealing the prevalence of DL-based Android malware detection and other defense approaches based on DL.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Hardware & Architecture
Xin Chen, Dongjin Yu, Xinxin Cai, He Jiang, Haihua Yu
Summary: MulFC is an unsupervised learning method for familiar analysis of malware, which identifies unknown malware families through multiple feature extraction and similarity calculation. Experimental results show that MulFC outperforms the state-of-the-art baseline method in terms of performance.
IEEE TRANSACTIONS ON RELIABILITY
(2023)
Article
Computer Science, Theory & Methods
Harshit Kumar, Biswadeep Chakraborty, Sudarshan Sharma, Saibal Mukhopadhyay
Summary: In this paper, a hardware-based malware detector (XMD) is proposed, which achieves better detection performance compared to currently used hardware performance counter (HPC) detectors. It is demonstrated that adding non-core telemetry channels improves the separability of benign and malware classes, resulting in performance gains. Experimental results show that XMD achieves a detection performance of 86.54% with a false positive rate of 2.9% on a mobile device.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
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
Fabricio Ceschin, Marcus Botacin, Heitor Murilo Gomes, Felipe Pinage, Luiz S. Oliveira, Andre Gregio
Summary: Malware poses a major threat to computer systems, and the constant evolution of malware samples causes concept drift, which directly affects the detection rates of machine learning models. This study evaluates the impact of concept drift on malware classifiers and proposes a novel data stream pipeline to mitigate the issue.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Amel Ksibi, Mohammed Zakariah, Latifah Almuqren, Ala Saleh Alluhaidan
Summary: The Internet of Things (IoT) is a dynamic sector in the international market, with Android driving its rapid development. Malware is a serious concern in the IoT, and this paper proposes a convolutional neural network-based approach for malware classification. The proposed method achieves higher accuracy compared to traditional methods and is more suitable for Android IoT devices due to its end-to-end learning process.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
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
Altyeb Altaher, Omar Barukab
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
(2017)
Article
Mathematics
Altyeb Taha
Summary: The continuous development of network technologies has led to the emergence of phishing websites as a major cybersecurity threat. Accurate detection of phishing websites is challenging and ensemble methods are considered state-of-the-art solutions. This paper proposes an intelligent ensemble learning approach based on weighted soft voting, achieving high accuracy in phishing website detection.
Article
Mathematics
Altyeb Taha, Omar Barukab, Sharaf Malebary
Summary: The open-source nature of Android OS and the inclusion of third-party apps have led to potential threats to user privacy. This study introduces a novel fuzzy integral-based multi-classifier ensemble for Android malware classification, achieving a high accuracy rate of 95.08% in experiments.
Article
Green & Sustainable Science & Technology
Altyeb Taha, Omar Barukab
Summary: This paper proposes an ensemble learning method based on genetic algorithms for Android malware classification, which showed higher accuracy and precision in experiments.
Article
Computer Science, Information Systems
Altyeb Altaher Taha, Sharaf Jameel Malebary
Summary: This paper proposes a new ensemble learning approach for predicting type 2 diabetes using a hybrid meta-classifier of fuzzy clustering and logistic regression. Experimental results demonstrate that the proposed method outperforms other models in predicting diabetes accurately.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Artificial Intelligence
Altyeb Altaher Taha, Sharaf Jameel Malebary
Summary: The proposed hybrid approach integrating FCM algorithm and LightGBM improves the classification efficiency of Android malicious apps by utilizing fuzzy clustering and machine learning techniques, achieving higher accuracy and learning efficiency.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Altyeb Altaher, Omar Mohammed Barukab
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY
(2019)
Article
Computer Science, Information Systems
Altyeb Altaher, Omar M. Barukab
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY
(2018)
Article
Multidisciplinary Sciences
Altyeb Altaher
INTERNATIONAL JOURNAL OF ADVANCED AND APPLIED SCIENCES
(2017)
Article
Computer Science, Theory & Methods
Altyeb Altaher, Omar Mohammed Barukab
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2017)
Article
Computer Science, Theory & Methods
Altyeb Altaher
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2017)
Article
Computer Science, Theory & Methods
Altyeb Altaher
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS
(2017)
Article
Computer Science, Information Systems
Altyeb Altaher, Omar BaRukab
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY
(2017)
Article
Computer Science, Information Systems
Altyeb Altaher Taha, Sharaf Jameel Malebary