On the automatic categorisation of android applications

Urquijo, Borja Sanz; Santos, Igor; Laorden, Carlos; Ugarte-Pedrero, Xabier; Bringas, Pablo García

doi:10.1109/ccnc.2012.6181075

Cited by 68 publications

(55 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the unsustainable growth of Android phone activations led to the number of malware samples increasing exponentially [11]. Developers and organizations started collecting sufficient samples of Android malwares.…”

Section: Detection Approachesmentioning

confidence: 99%

“…Other example, Sanz, Santos, and Laorden proposed an automatic categorization of Android applications [11]. The main concept is to provide an automatically characterization for different types of applications.…”

Section: ____________________________________________________________mentioning

confidence: 99%

“…Zhao, Zhang, Ge, and Yuan have proposed a solution to monitor system calls in runtime without malwares having the ability of noticing the detector presences [11]. They developed an application for Android smartphone called RobotDroid, which is a software behavior signature, based on malware detection framework.…”

Section: Malware Detection In Smartphonementioning

confidence: 99%

“…For example, Forrest has presented typical host-based anomaly detection for Android smartphone that takes power-consumption into consideration [11]. Hostbased anomaly detection is a way of monitoring system call sequence stored in the database.…”

Section: Malware Detection In Smartphonementioning

confidence: 99%

See 3 more Smart Citations

Android Mobile Platform Security and Malware Survey

.¹

2013

IJRET

View full text Add to dashboard Cite

show abstract

Section: Detection Approachesmentioning

confidence: 99%

Section: ____________________________________________________________mentioning

confidence: 99%

Section: Malware Detection In Smartphonementioning

confidence: 99%

Section: Malware Detection In Smartphonementioning

confidence: 99%

See 2 more Smart Citations

Android Mobile Platform Security and Malware Survey

.¹

2013

IJRET

View full text Add to dashboard Cite

show abstract

“…The aim is to find the hyper plane to classify samples. In Android malware detection, SVM and other machine learning algorisms are usually use to detect the malicious application depending on the source code [20].…”

Section: N-gram Svm and Gamentioning

confidence: 99%

Detecting Applications with Malicious Behavior in Android Device Based on GA and SVM

Liu¹,

Yang²,

Zhang³

2018

Proceedings of the 2017 2nd International Conference on Electrical, Control and Automation Engineering (ECAE 2017)

View full text Add to dashboard Cite

Abstract-In recent years, mobile technology and mobile-device have been rapidly developed. Since mobile devices collect and transmit large amounts of private information about users, malicious applications will pose a significant threat to the privacy and property security of the individual. Openness is a crucial factor why Android becomes the most popular mobile operate system, but it also results the Android system vulnerable to malware. In this paper, the n-gram opcode is employed to describe the applications, and then a static analysis method based on genetic algorithm and support vector machine is used to detect applications with malicious behaviors.

show abstract