Permission based malware detection in android devices

@inproceedings{Ilham2018PermissionBM,
  title={Permission based malware detection in android devices},
  author={Soussi Ilham and Ghadi Abderrahim and Boudhir Anouar Abdelhakim},
  booktitle={SCA '18},
  year={2018}
}
The mobile operation system Android is one of the most OS's used in the entire world, which make it the target of many malware projects and the mission of detecting those malware applications is getting harder over time due to evaluation and development of techniques that make possible for those malwares to hide their maliciousness activities from anti-malware techniques by obfuscating the code source of application or even hiding malicious activities when it's getting to scan by an anti… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • The Experiment shows that the most ranked features in common between CFS, Gain Ratio, Information Gain, Correlation Coefficient and Relief are: RECEIVE, SEND_SMS, RECEIVE_SMS, READ_PHONE_STATE, READ_EXTERNAL_STORAGE, RESTART_PACKAGES Using feature selection algorithms in the experiment did not improve the accuracy results but the opposite, all experiments results were near to 93% and 6% for misclassified samples whereas experiments using the overall set of features (permissions) obtained better accuracy results with 98%.