Intersection Features for Android Botnet Classification
Najiahtul Syafiqah Ismail1, Robiah Yusof2, Halizah Saad3, Mohd Faizal Abdollah4
1Najiahtul Syafiqah Ismail*, Faculty of Information and Communication Technology, University Technical Malaysia.
2Melaka (UTeM), Melaka, Malaysia. Robiah Yusof, Faculty of Information and Communication Technology, University Technical Malaysia Melaka (UTeM), Melaka, Malaysia.
3Mohd Faizal Abdollah, Faculty of Information and Communication Technology, University Technical Malaysia.
4Melaka (UTeM), Melaka, Malaysia. Halizah Saad, Faculty of Information and Communication Technology, University Technical Malaysia Melaka (UTeM), Melaka, Malaysia.
Manuscript received on November 11, 2019. | Revised Manuscript received on November 23, 2019. | Manuscript published on 30 November, 2019. | PP: 4422-4427 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8383118419/2019©BEIESP | DOI: 10.35940/ijrte.D8383.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The evolution of the Internet of things (IoT) has made a significant impact and availed opportunities for mobile device usage on human life. Many of IoT devices will be supposedly controlled through a mobile, giving application (apps) developers great opportunities in the development of new applications. However, hackers are continuously developing malicious applications especially Android botnet to steal private information, causing financial losses and breach user privacy. This paper proposed an enhancement approach for Android botnet classification based on features selection and classification algorithms. The proposed approach used requested permissions in the Android app and API function as features to differentiate between the Android botnet apps and benign apps. The Chi Square was used to select the most significant permissions, then the classification algorithms like Naïve Bayes and Decision Tree were used to classify the Android apps as botnet or benign apps. The results showed that Decision Tree with Chi-Square feature selection achieved the highest detection accuracy of 98.6% which was higher than other classifiers.
Keywords: Mobile Malware, Android Botnet; IoT, Malware Classification.
Scope of the Article: Classification.