Analysis of Features Selection and Machine Learning Classifier in Android Malware Detection

Mas'ud, M. Z.; Sahib, Shahrin; Abdollah, Mohd Faizal; Selamat, Siti Rahayu; Yusof, Robiah

doi:10.1109/icisa.2014.6847364

Cited by 57 publications

(26 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chi-Square, relief and information gain are the most popular filter approach [14], however we propose a new feature selection method named PCA_RELIEF based on PCA and relief which performs a high accuracy rate in our experiment.…”

Section: Related Workmentioning

confidence: 99%

An Android malware detection system based on machine learning

Wen¹,

Yu²

2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. The Android smartphone, with its open source character and excellent performance, has attracted many users. However, the convenience of the Android platform also has motivated the development of malware. The traditional method which detects the malware based on the signature is unable to detect unknown applications. The article proposes a machine learning-based lightweight system that is capable of identifying malware on Android devices. In this system we extract features based on the static analysis and the dynamitic analysis, then a new feature selection approach based on principle component analysis (PCA) and relief are presented in the article to decrease the dimensions of the features. After that, a model will be constructed with support vector machine (SVM) for classification. Experimental results show that our system provides an effective method in Android malware detection.

show abstract

Section: Related Workmentioning

confidence: 99%

An Android malware detection system based on machine learning

Wen¹,

Yu²

2017

AIP Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…However, the dimensions of features are too large which may introduce a very high computational overhead, which will impact the detection results [27]. In addition, some features are common in both the normal and malware samples, which may downgrade the overall quality of the classification model, such as WRITE EXTERNAL STORAGE, a permission used to obtain privilege to write data on SD card.…”

Section: Feature Selectionmentioning

confidence: 99%

Mlifdect: Android Malware Detection Based on Parallel Machine Learning and Information Fusion

Wang

Zhang

et al. 2017

Security and Communication Networks

View full text Add to dashboard Cite

In recent years, Android malware has continued to grow at an alarming rate. More recent malicious apps' employing highly sophisticated detection avoidance techniques makes the traditional machine learning based malware detection methods far less effective. More specifically, they cannot cope with various types of Android malware and have limitation in detection by utilizing a single classification algorithm. To address this limitation, we propose a novel approach in this paper that leverages parallel machine learning and information fusion techniques for better Android malware detection, which is named Mlifdect. To implement this approach, we first extract eight types of features from static analysis on Android apps and build two kinds of feature sets after feature selection. Then, a parallel machine learning detection model is developed for speeding up the process of classification. Finally, we investigate the probability analysis based and Dempster-Shafer theory based information fusion approaches which can effectively obtain the detection results. To validate our method, other state-of-the-art detection works are selected for comparison with real-world Android apps. The experimental results demonstrate that Mlifdect is capable of achieving higher detection accuracy as well as a remarkable run-time efficiency compared to the existing malware detection solutions.

show abstract

“…Totally 34 behavior monitoring items are customized, which are behavior characteristics. Mas' et al [5] performing feature selection can improve detection efficiency.…”

Section: Malware Monitoringmentioning

confidence: 99%

Host Security Based Research on Automatic Generation Method of Security Threat Intelligence

Chen¹,

Chang²

2017

dtcse

View full text Add to dashboard Cite

Abstract. In order to conduct in-depth analysis on the operating principle of malware and reduce its analysis period, this article proposes a behavior analysis based malware family clustering method; it conducts deeper layer behavior correlation analysis according to sample selection of different families, to generate the Security Threat Intelligence representing for the malwares of this family. It is beneficial to the rapid expansion of antimalware engine behavior library, and can give active response to host computer security events, to detect malware variants. According to experimental findings, this method can extract effective Security Threat Intelligence, detect malware quite effectively and efficiently.

show abstract

Analysis of Features Selection and Machine Learning Classifier in Android Malware Detection

Cited by 57 publications

References 5 publications

An Android malware detection system based on machine learning

An Android malware detection system based on machine learning

Mlifdect: Android Malware Detection Based on Parallel Machine Learning and Information Fusion

Host Security Based Research on Automatic Generation Method of Security Threat Intelligence

Contact Info

Product

Resources

About