Spyware Detection in Android Using Hybridization of Description Analysis, Permission Mapping and Interface Analysis

Kaur, Parmjit; Sharma, Sumit

doi:10.1016/j.procs.2015.02.148

Cited by 11 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is still some weakness in the existing approaches such as security resilience, connection probability and scalability. [131], MAPE [126], Linear SVM [128], IoT Malware Detection [127], ELSA [130], Hybrid Spyware Detection [129], BLOWFISH, PRESENT, HEIGHT, AES, 3DES, RSA, ECC, DSA, DH [233], [40], K-Anonymity Technique [135], BUDDIES [136], LSR [146], Lightweight RSS-Based Scheme [148], Privacy-Preserving Scheme [147], Game Theory [152], [153], [234], CHA-IDS [140], TCGA [145], INTI [143], Sensor Scheduling Technique [120], Mobile Agent-Based IDS [150], Determeministic Detection [156], Jammer Localization, Detection and Mitigation [157]- [159], [182], [189], [190] and Tamper Detection [160].…”

Section: A Discussion On Existing Security Approachesmentioning

confidence: 99%

“…The authors in [127] studied industrial mobile-IoT malware detection techniques and analyzed them in terms of static, dynamic, and hybrid approaches. A hybrid approach is proposed in [129] for detecting Spyware using and comparing various antivirus software. This technique is based on three parameters: description mapping, interface analysis and source code analysis.…”

Section: B Autonomic Approachesmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Security Challenges, Attacks Taxonomy and Advanced Countermeasures in the Internet of Things

et al. 2020

View full text Add to dashboard Cite

Section: A Discussion On Existing Security Approachesmentioning

confidence: 99%

Section: B Autonomic Approachesmentioning

confidence: 99%

A Survey of Security Challenges, Attacks Taxonomy and Advanced Countermeasures in the Internet of Things

et al. 2020

View full text Add to dashboard Cite

“…Kaur et al [ 24 ] proposed a detection framework based on description analysis, permission mapping, and interface analysis. The researchers proposed gathering data from three primary sources, description mapping, interface layout, and source code analysis, along with all permissions gleaned from the XML file; thus, these data are used to create pre-digital signatures for applications that may engage in espionage activities.…”

Section: Background and Related Workmentioning

confidence: 99%

Android Spyware Detection Using Machine Learning: A Novel Dataset

Qabalin

Naser

Alkasassbeh

2022

Sensors

View full text Add to dashboard Cite

Smartphones are an essential part of all aspects of our lives. Socially, politically, and commercially, there is almost complete reliance on smartphones as a communication tool, a source of information, and for entertainment. Rapid developments in the world of information and cyber security have necessitated close attention to the privacy and protection of smartphone data. Spyware detection systems have recently been developed as a promising and encouraging solution for smartphone users’ privacy protection. The Android operating system is the most widely used worldwide, making it a significant target for many parties interested in targeting smartphone users’ privacy. This paper introduces a novel dataset collected in a realistic environment, obtained through a novel data collection methodology based on a unified activity list. The data are divided into three main classes: the first class represents normal smartphone traffic; the second class represents traffic data for the spyware installation process; finally, the third class represents spyware operation traffic data. The random forest classification algorithm was adopted to validate this dataset and the proposed model. Two methodologies were adopted for data classification: binary-class and multi-class classification. Good results were achieved in terms of accuracy. The overall average accuracy was 79% for the binary-class classification, and 77% for the multi-class classification. In the multi-class approach, the detection accuracy for spyware systems (UMobix, TheWiSPY, MobileSPY, FlexiSPY, and mSPY) was 90%, 83.7%, 69.3%, 69.2%, and 73.4%, respectively; in binary-class classification, the detection accuracy for spyware systems (UMobix, TheWiSPY, MobileSPY, FlexiSPY, and mSPY) was 93.9%, 85.63%, 71%, 72.3%, and 75.96%; respectively.

show abstract