An Android Malware Detection System Based on Feature Fusion

Li, Jian; Wang, Zheng; Wang, Tao; Tang, Jinghao; Yang, Yuguang; Zhou, Yi‐Hua

doi:10.1049/cje.2018.09.008

Cited by 17 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Meanwhile, Ref. [94] used a resampling technique to address an unbalanced dataset. Recently, researchers have created a database named RmvDroid [95], which claimed to be the first large-scale and reliable Android malware dataset.…”

Section: A Sample Acquisitionmentioning

confidence: 99%

“…In the data cleaning phase of preprocessing, some researchers remove unnecessary features based on subjective judgment from a macro perspective, such as Refs. [94] and [102]. Meanwhile, some researchers clean up the data according to the requirements of subsequent processing steps.…”

Section: ) Data Preprocessingmentioning

confidence: 99%

“…[102] System calls that are never invoked by any application in the dataset are removed. [94] There are a lot of ambiguous vectors in the eigenvector matrix, which will affect the performance of the classifier. By removing these ambiguous vectors, the effect of classification can be improved.…”

Section: ) Feature Selectionmentioning

confidence: 99%

“…For example, Ref. [94] divides the 377 features used into 10 categories, among which the IP address is derived from both static source code analysis and dynamic behavioral analysis. The researchers in Ref.…”

Section: ) Hybrid Featuresmentioning

confidence: 99%

“…[3], [90], [94], [102], [105], [108], [109], [111], [114], [115], [119] , [139], [142], [145], [147], [150]- [153], [163], [170], [171], [173], [177], [179], [186], [189], [190], [192], [193], [195], [200], [205], [206], [208], [215], [245] Online Learning (OL)…”

Section: ) Machine Learning Models and Algorithms Used In Android Maunclassified

See 4 more Smart Citations

A Review of Android Malware Detection Approaches Based on Machine Learning

et al. 2020

View full text Add to dashboard Cite

Android applications are developing rapidly across the mobile ecosystem, but Android malware is also emerging in an endless stream. Many researchers have studied the problem of Android malware detection and have put forward theories and methods from different perspectives. Existing research suggests that machine learning is an effective and promising way to detect Android malware. Notwithstanding, there exist reviews that have surveyed different issues related to Android malware detection based on machine learning. We believe our work complements the previous reviews by surveying a wider range of aspects of the topic. This paper presents a comprehensive survey of Android malware detection approaches based on machine learning. We briefly introduce some background on Android applications, including the Android system architecture, security mechanisms, and classification of Android malware. Then, taking machine learning as the focus, we analyze and summarize the research status from key perspectives such as sample acquisition, data preprocessing, feature selection, machine learning models, algorithms, and the evaluation of detection effectiveness. Finally, we assess the future prospects for research into Android malware detection based on machine learning. This review will help academics gain a full picture of Android malware detection based on machine learning. It could then serve as a basis for subsequent researchers to start new work and help to guide research in the field more generally.

show abstract

Section: A Sample Acquisitionmentioning

confidence: 99%

Section: ) Data Preprocessingmentioning

confidence: 99%

Section: ) Feature Selectionmentioning

confidence: 99%

Section: ) Hybrid Featuresmentioning

confidence: 99%

Section: ) Machine Learning Models and Algorithms Used In Android Maunclassified

See 3 more Smart Citations

A Review of Android Malware Detection Approaches Based on Machine Learning

et al. 2020

View full text Add to dashboard Cite

show abstract

DroidDeep: using Deep Belief Network to characterize and detect android malware

Shi

et al. 2020

Soft Comput

View full text Add to dashboard Cite

Applications of spiking neural P systems in cybersecurity

Pleṣa,

Gheorghe,

Ipate

et al. 2024

J Membr Comput

View full text Add to dashboard Cite

Spiking neural P systems are third-generation neural networks that are much more energy efficient than the current ones. In this paper, we investigate for the first time the possibility of using spiking neural P systems to solve cybersecurity-related problems. We proposed a new architecture called cyber spiking neural P systems (Cyber-SN P systems for short), which is designed especially for cybersecurity data and problems. We trained multiple Cyber-SN P systems to detect malware on the Android platform, phishing websites, and spam e-mails. We show through experiments that these networks can efficiently classify cybersecurity-related data with much fewer training epochs than perceptron-based artificial neural networks.

show abstract

An Android Malware Detection System Based on Feature Fusion

Cited by 17 publications

References 15 publications

A Review of Android Malware Detection Approaches Based on Machine Learning

A Review of Android Malware Detection Approaches Based on Machine Learning

DroidDeep: using Deep Belief Network to characterize and detect android malware

Applications of spiking neural P systems in cybersecurity

Contact Info

Product

Resources

About