Android Malware Detection using Multilayer Autoencoder and Random Forest

Android Malware Detection using Multilayer Autoencoder and Random Forest

  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-11
Year of Publication : 2022
Authors : A. Lakshmanarao, M. Shashi
DOI : 10.14445/22315381/IJETT-V70I11P227

How to Cite?

A. Lakshmanarao, M. Shashi, "Android Malware Detection using Multilayer Autoencoder and Random Forest," International Journal of Engineering Trends and Technology, vol. 70, no. 11, pp. 249-257, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I11P227

Abstract
One of the most challenging concerns in the world of operating systems and software is the presence of malicious software. The Android operating system is also experiencing the same issues. Because of the significant increase in the refinement of Android malware obfuscation and detection avoidance methods, a significant number of conventional malware investigative techniques have become outdated. The malware detection approach based on earlier signatures is ineffective for detecting unknown threats. In recent years, machine learning and deep learning techniques have proved promising for malware detection. A framework is proposed to extract several features like permissions, opcodes, api packages, system calls, intents, and api calls from Android malware and benign apps and to build a classifier for malware detection using the most suitable machine learning and deep learning algorithms. Based on the performance analysis Random Forest algorithm was identified as the suitable classifier as it produced the highest accuracy on raw input. In order to further improve the accuracy, this paper proposes a cascade of multilayer autoencoder for feature extraction followed by the random forest classifier for Android malware detection. A cascade of an autoencoder and random forest was applied to real-world datasets and achieved an accuracy of 99.1%. The proposed work also individually examines the impact of the six types of features to distinguish malware and benign apps.

Keywords
Android Malware, Random Forest, Multilayer Autoencoder.

Reference
[1] M. Kumaran and W. Li, "Lightweight Malware Detection Based on Machine Learning Algorithms and the Android Manifest File," IEEE MIT Undergraduate Research Technology Conference (URTC), pp. 1-3, 2016. Crossref, https://doi.org/10.1109/URTC.2016.8284090
[2] A. Fatima, R. Maurya, M. K. Dutta, R. Burget and J. Masek, "Android Malware Detection Using Genetic Algorithm-based Optimized Feature Selection and Machine Learning," 2019 42nd International Conference on Telecommunications and Signal Processing (TSP), pp. 220-223, 2019. Crossref, https://doi.org/10.1109/TSP.2019.8769039
[3] Sirisha.P, K. P. B., A. K. K. and A. T, "Detection of Permission Driven Malware in Android Using Deep Learning Techniques," 2019 3rd International Conference on Electronics, Communication and Aerospace Technology (ICECA), pp. 941-945, 2019. Crossref,
https://doi.org/10.1109/ICECA.2019.8821811
[4] Dr.S.Masood Ahamed and Dr.V.N.Sharma, "Malware Detection using Optimized Random Forest Classifier within Mobile Devices," SSRG International Journal of Computer Science and Engineering, vol. 3, no. 5, pp. 90-99, 2016. Crossref, https://doi.org/10.14445/23488387/IJCSE-V3I5P118
[5] X. Su, D. Zhang, W. Li and K. Zhao, "A Deep Learning Approach to Android Malware Feature Learning and Detection," 2016 IEEE Trustcom/BigDataSE/ISPA, pp. 244-251, 2016. Crossref, https://doi.org/10.1109/TrustCom.2016.0070
[6] T. Kim, B. Kang, M. Rho, S. Sezer and E. G. Im, "A Multimodal Deep Learning Method for Android Malware Detection Using Various Features," in IEEE Transactions on Information Forensics and Security, vol. 14, no. 3, pp. 773-788, 2019. Crossref, https://doi.org/10.1109/TIFS.2018.2866319
[7] A. Lakshmanarao and M.Shashi, "Android Malware Detection Using Convolutional Neural Networks," In Data Engineering and Intelligent Computing Advances in Intelligent Systems and Computing, vol. 1407, pp. 151-162, 2021. Crossref, https://doi.org/10.1007/978-981-16-0171-2_15
[8] Lakshmanarao. A and Shashi. M, "An Efficient Android Malware Detection Framework with Stacking Ensemble Model," International Journal of Engineering Trends and Technology, vol. 70, no. 4, pp. 294-302, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I4P226
[9] Omar N. Elayan and Ahmad M. Mustafa, "Android Malware Detection Using Deep Learning," Procedia Computer Science, vol. 184, pp. 847-852, 2021. https://doi.org/10.1016/j.procs.2021.03.106
[10] Tianliang Lu, Yanhui Du, Li Ouyang, Qiuyu Chen and Xirui Wang, "Android Malware Detection Based on a Hybrid Deep Learning Model," Security and Communication Networks, vol. 2020, pp. 11, 2020. Crossref, https://doi.org/10.1155/2020/8863617
[11] Syeda Sara Samreen and Hakeem Aejaz Aslam, "Hyperspectral Image Classification using Deep Learning Techniques: A Review," SSRG International Journal of Electronics and Communication Engineering, vol. 9, no. 6, pp. 1-4, 2022. Crossref, https://doi.org/10.14445/23488549/IJECE-V9I6P101
[12] Gianni D'Angelo, Massimo Ficco and Francesco Palmieri, "Malware Detection in Mobile Environments Based on Autoencoders and API-Images," Journal of Parallel and Distributed Computing, vol. 137, pp. 26-33, 2020. Crossref, https://doi.org/10.1016/j.jpdc.2019.11.001
[13] X. Xing, X. Jin, H. Elahi, H. Jiang and G. Wang, "A Malware Detection Approach Using Autoencoder in Deep Learning," IEEE Access, vol. 10, pp. 25696-25706, 2022. Crossref, https://doi.org/10.1109/ACCESS.2022.3155695
[14] K.Aishwarya and C.Selvi, "Predicting Fraud Apps using Hybrid Learning Approach," SSRG International Journal of Computer Science and Engineering, vol. 5, no. 6, pp. 1-5, 2018. Crossref, https://doi.org/10.14445/23488387/IJCSE-V5I6P103
[15] Nektaria Potha, V. Kouliaridis and G. Kambourakis, "An Extrinsic Random-Based Ensemble Approach for Android Malware Detection," Connection Science, vol. 33, no. 4, pp. 1077-1093, 2021. Crossref, https://doi.org/10.1080/09540091.2020.1853056
[16] Parnika Bhat and Kamlesh Dutta, "A Multi-Tiered Feature Selection Model for Android Malware Detection Based on Feature Discrimination and Information Gain," Journal of King Saud University - Computer and Information Sciences, 2021. Crossref, https://doi.org/10.1016/j.jksuci.2021.11.004
[17] Immadi Murali Krishna, Pendem Durga Bhavani, Tiriveedhi M S Madhuvani and Vajja Poojitha, "An Effective Segmentation and modified Ada Boost CNN based classification model for Fabric Fault Detection system," SSRG International Journal of Computer Science and Engineering, vol. 7, no. 7, pp. 34-40, 2020. Crossref, https://doi.org/10.14445/23488387/IJCSE-V7I7P106
[18] Atika Gupta, Sudhanshu Maurya, Divya Kapil, Nidhi Mehra and Harendra Singh Negi, "Android Malware Detection using Machine Learning," International Journal of Recent Technology and Engineering, vol. 8, no. 2S12, 2019.
[19] Rana, M. S., Sung and A. H, "Malware Analysis on Android Using Supervised Machine Learning Techniques," International Journal of Computer and Communication Engineering, vol. 7, no. 4, pp. 178-188, 2018.
[20] Lakshmanarao A, and Shashi M, "Android Malware Detection with Deep Learning using RNN from Opcode Sequences," International Journal of Interactive Mobile Technologies (iJIM), vol. 16, no. 1, pp. 145–157, 2022. Crossref, https://doi.org/10.3991/ijim.v16i01.26433
[21] Oyinloye Oghenerukevwe Elohor, Olatomide Awoyomi, "Modelling A Data Sniffing Malware Detector For Apks," International Journal of Computer and Organization Trends, vol. 9, no. 6, pp. 1-8, 2019. Crossref, https://doi.org/10.14445/22492593/IJCOT-V9I6P301
[22] [Online]. Available: unb.ca/cic/datasets/andmal2017.html
[23] M. Gohari, S. Hashemi and L. Abdi, "Android Malware Detection and Classification Based on Network Traffic Using Deep Learning," 2021 7th International Conference on Web Research(ICWR), pp. 71-77, 2021. Crossref, https://doi.org/10.1109/ICWR51868.2021.9443025
[24] Hui-Juan Zhu, Tong-Hai Jiang, Bo Ma, Zhu-Hong You, Wei-Lei Shi and Li Cheng, "HEMD: A Highly Efficient Random Forest-Based Malware Detection Framework For Android," Neural Comput & Application, vol. 30, pp. 3353–3361, 2018. Crossref, https://doi.org/10.1007/s00521-017-2914-y
[25] Weiqing Huang, Erhang Hou, Liang Zheng and Weimiao Feng, "MixDroid: A Multi-Features and Multiclassifiers Bagging System for Android Malware Detection," AIP Conference Proceedings, vol. 1967, pp. 020015, 2018. Crossref, https://doi.org/10.1063/1.5038987
[26] Meghna Dhalaria and Ekta Gandotra, "A Hybrid Approach for Android Malware Detectionand Family Classification," International Journal of Interactive Multimedia and Artificial Intelligence, vol. 6, no. 6, 2020. Crossref, https://doi.org/10.9781/ijimai.2020.09.001