A Systematic Overview of Android Malware Detection

Figures & data

Figure 1. Android OS architecture.

Figure 2. Detailed process of feature selection.

Table 1. Summary of Android feature extraction

Reference	Features	Type	Classifiers
(Onwuzurike et al. 2017)	API calls	Dynamic analysis	RF, KNN, SVM
(Cai et al. 2016)	Behavioral features	Dynamic analysis	RF, SVM, DT, KNN, NB
(Afonso et al., 2015)	API calls and system call traces	Dynamic analysis	RF
(Dash et al. 2016)	System calls	Dynamic analysis	SVM
(Kumar et al. 2019)	Manifest files, decompiling DEX, shared libraries	Static analysis	DNN
(Nicheporuk et al., 2020)	APIs, permissions	Static analysis	CNN
(Cai et al. 2021)	Function call graph	Static analysis	SVM
(Gao 2019)	Strings, function call graph	Static analysis	SVM, KNN, RF
(Lu et al. 2019)	API calls	Static analysis	Bidirectional LSTM
(Yung and Juang 2017)	Permission, activity, service, receiver, sensitive strings, dexclass etc.	Hybrid analysis	SVM
(Chen et al. 2016)	Permissions, API calls, sensitive information request	Hybrid analysis	SVM, MLP, NB, IBK, Bagging

Table 2. Data preprocessing of Android raw features

Reference	Description	Type
(Bai et al. 2020)	FAMD combined filter, wrapper, and embedded based feature selection method.	Data cleaning
(Xu et al. 2018)	The N-Gram technique was used to remove irrelevant API subsequences.	Data cleaning
(Pang et al.2019)	This paper removed redundant features based on feature weighting	Data cleaning
(Bai et al. 2020)	FAMD used integration of permissions and Dalvik opcode sequences.	Data integration
(Qiu et al. 2019)	A3CM combined API calls and network addresses.	Data integration
(Nicheporuk et al. 2020)	API method calls and permissions were the input of a convolutional neural network.	Data integration
(Xu et al. 2018)	Static features and dynamic features were combined.	Data integration
(Yerima and Sezer 2019)	Android permissions and API calls were used as multi-source data using static analysis.	Data integration
(Naway and Li 2019)	The integration of permission, intention filter, API call, and invalid certificate was used.	Data integration
(Bai et al. 2020)	The N-Gram technique and the FCBF algorithm were used to reduce dimensionality.	Data reduction
(Alam, Alharbi and Yildirim 2020)	This paper reduced data by DroidDomTree that mines the dominance tree of API calls.	Data reduction
(Lu et al. 2019)	Redundant N-Gram subsequences were removed using Information Gain.	Data reduction
(Li et al. 2018)	Attribute Subset Selection and Principal Component Analysis were used to reduce dimensionality.	Data reduction
(Li et al. 2018)	Three levels of permission feature pruning methods were presented	Data reduction
(Fatima et al.2019)	Evolutionary genetic algorithm was applied for feature selection.	Data reduction
(Cai, Li and Xiong 2021)	Feature weighting was employed to reduce data.	Data reduction
(Kim et al. 2018)	Image embedding method was used to reduce dimension of different graphs.	Data reduction
(Li et al. 2017)	Android malware clustering system was adopted through iterative mining of malicious payload.	Data reduction
(Bakour and Ünver 2021)	The source of APK was converted into grayscale images and processed by deep learning.	Data transformation
(Cai et al. 2021)	API sequence was converted to the enhanced function call graphs.	Data transformation
(Fan et al. 2018)	Raw data of API call sequence and sensitive data were converted to frequent subgraphs.	Data transformation
(Yen and Sun 2019)	This paper digitized the importance of the word and converted them to images.	Data transformation
(Mercaldo and Santone 2021)	Features were presented in a form of audio files.	Data transformation
(Ünver and Bakour 2020)	The AndroidManifest.xml in samples was used to constructed grayscale image datasets.	Data transformation
(Vasan et al. 2020)	Raw malware binaries were converted into color images.	Data transformation

Table 3. Feature subsets selection in Android

Method	Description	characteristics	Algorithms
Filter	The model is independent of any result of classifier	Fast, lower computational cost but without considering feature relevance	Correlation-based Feature Selection (CFS), Consistency-based Filter (Dash and Liu 2003),Information Gain (Yerima, Sezer and Sezer 2014),ReliefF(Spolar et al.2013)
Wrapper	The model uses the accuracy of the classifier to evaluate the quality of the generated feature subset	Capture feature relevance, optimize a predictor but high computational cost	FFSR (Ye and Gong 2010),WrapperSubsetEval (Witten and Frank 2011)

Figure 3. Categories of feature selection.

Table 4. Summary of Android malware detection technology

Year	Reference	Detection technology	Description
2018	(Saracino et al. 2018)	Signature and heuristics	Host-based malware detection system
2018	(Sihwail, Omar and Ariffin 2018)	Signature and heuristics	A review of signature and heuristics method
2018	(Rehman et al. 2018)	Signature and heuristics	A hybrid framework using signature and heuristics method
2021	(Li et al., 2021)	Heuristics	A review of heuristic malware detection
2010	(Firdausi et al. 2010)	Heuristics	Five classifiers were compared to verify the effectiveness of heuristics analysis
2020	(Alazab et al. 2020)	Heuristics	Integrate permissions with API calls based on heuristic analysis
2015	(Talha, Alper and Aydin 2015)	Heuristics	A permission-based Android malware detection system using heuristic analysis
2020	(Priya and Visalakshi 2020)	Machine learning	The KNN-based Relief algorithm and the optimized SVM were adopted to detect Android malware.
2018	(Chen et al. 2018)	Machine learning	Generate adversarial samples to evade the detection of current machine learning based detectors.
2020	(Pektaş and Acarman, 2020a)	Machine learning	Employ deep neural network as malware classification.
2019	(Kumar et al. 2019)	Machine learning	Combine dynamic analysis and static analysis machine learning.
2020	(Pektaş and Acarman, 2020b)	Machine learning	Deep learning was applied using features extracted from instruction call graphs
2018	(Hasegawa and Iyatomi 2018)	Machine learning	One-dimensional convolutional neural networks was applied for Android malware detection.
2019	(Yen and Sun 2019)	Machine learning	Utilize CNN to process images generated from the importance of words

Table 5. Machine learning models applied in Android malware detection categorized by learning type

Learning type	Models	Reference
Supervised learning	1.DT	(Mantoo 2020)
	2.NB	(Firdaus et al. 2018)
	3.KNN	(Mantoo 2020)
	4.SVM	(Mantoo 2020)
Semi-supervised learning	1.SSL-NNR	(Taheri et al. 2020) (Chen et al. 2017)
	2.GIL	(Atzeni et al. 2018)
	3.Laplace SVM	(Mahdavifar et al. 2020) (Ribeiro et al. 2020)
Unsupervised learning	1.K-means	(Fan et al. 2019)
	2.PCA	(Wen and Yu 2017) (Tiwari and Shukla 2018)
	3.SVD	(Singh et al. 2021)
	4.ICA	(Zhang et al2015)
Reinforcement learning	1.Q-Learning	(Fang et al. 2019)
	2.DQN, DDQN	(Rathore et al.2020)
	3.A2C, A3C	(Khowaja and Khuwaja 2021)

Table 6. Summary of machine learning models in Android malware detection

Model	Advantages	Disadvantages	Reference
Linear Model	The main algorithm of statistics; direct and fast	The premise of the algorithm is strict, and is unable to deal with high-dimensional Android features	(Ham et al. 2014)(Zhang et al. 2019)
Support Vector Machine	Easy to deal with small-scale; low dimensional and nonlinear problems	Large amount of data preprocessing; sensitive to missing values	(Mantoo 2020)(Faiz, Hussain and Marchang 2020)
Naive Bayes	Model training is simple and fast	Not available when the extracted features are correlated	(Firdaus et al. 2018)
Decision Tree	Capable to deal with large-scale and missing value model	Conspire toward overfitting; does not support online learning	(Mantoo 2020)(Lashkari et tl. 2018)
Deep Learning	Address difficult problems by complex model with more parameters	Low training efficiency of complex model; easy to be overfitting	(Murtaz et al. 2018)(McLaughlin et al. 2017)
Random Forest	Easy to implement; low computational overhead; strong generalization ability	The initial performance of random forest is unsatisfactory	(Lashkari et al. 2017)(Murtaz et al. 2018)
Neural Network	High accuracy and strong fault tolerance	Requires a lot of training data; the parameters and topology are difficult to choose	(Nisa et al. 2020)(Zhu et al. 2018)
K-nearest Neighbor	Can be implemented without parameter estimation; suitable for solving multi-classification problems	Allergic to the dataset; the amount of calculation is relatively large	(Mantoo 2020) (Priya and Visalakshi 2020)(Lashkari et al. 2017)
K-means Clustering	Low computational overhead	The results are affected by the initial settings; sensitive to noise and discrete values	(Ilham, Abderrahim and Abdelhakim 2018)(Faiz, Hussain and Marchang 2020)

Table 7. Security attacks of machine learning models

Threat types	Attack method	Description	Reference
Training integrity threat	Poison attack	The attacked model is unable to work appropriately in the test phase with poisoned data mixed into the training dataset.	(Biggio, Nelson and Laskov 2013)
	Backdoor attack	The attacked model classifies the data of the backdoor trigger into the target category due to the poisoned training set.	(Gu, Dolan-Gavitt, and Garg 2019) (Liu et al. 2018)
Test integrity threats	Adversarial sample attack	The attacked model is cheated by adversarial samples that are deliberately added with subtle interference	(Kurakin, Goodfellow and Bengio 2019) (Carlini and Wagner 2017)
Lack of robustness of the model	Not explainable	Machine learning models cannot be clearly explained how it makes decisions and why it performs well	(Papernot and Nicolas 2018)
	Insufficient training data	It destroys the adaptability of the machine learning model confronted with the changing environment for the insufficient training dataset	(Papernot and Nicolas 2018)

Onwuzurike, L., E. Mariconti, P. Andriotis, E. Cristofaro, G. Ross, and G. Stringhini. 2017. MaMaDroid: detecting android malware by building markov chains of behavioral models (Extended version). ACM Transactions on Privacy and Security (TOPS) 22 (2):14. 2019.

 Web of Science ®Google Scholar

Cai, H., N. Meng, and B. Ryder, Yao, D. 2016. DroidCat: unified dynamic detection of android malware https://vtechworks.lib.vt.edu/handle/10919/77523. .

 Google Scholar

Afonso, V. M., M. F. de Amorim, A. R. A. Grégio, G. B. Junquera, and P. L. de Geus. 2015. Identifying Android malware using dynamically obtained features. Journal of Computer Virology & Hacking Techniques 11 (1):9–524. 2015. doi:10.1007/s11416-014-0226-7.

 Web of Science ®Google Scholar

Dash, S., G. Suarez-Tangil, S. Khan, K. Tam, and R. Holloway. 2016. DroidScribe: classifying android malware based on runtime behavior 2016 IEEE Security and Privacy Workshops (SPW) 22-26 May 2016 San Jose, CA. 252–61 doi:10.1109/SPW.2016.25.

 Google Scholar

Kumar, R., X. Zhang, Wang W., R. U. Khan, J. Kumar, and A. Sharif. 2019. A multimodal malware detection technique for android iot devices using various features. IEEE Access 7:64411–30. doi:10.1109/ACCESS.2019.2916886.

 Web of Science ®Google Scholar

Nicheporuk, A., Savenko, O., A. Nicheporuk, and Y. Nicheporuk. 2020. An android malware detection method based on CNN mixed-data model CEUR Workshop Proceedings Kharkiv, Ukraine. 2732:198–213.

 Google Scholar

Cai, M., Jiang, Y., C. Gao, Li, H., and Yuan W. 2021. Learning features from enhanced function call graphs for Android malware detection. Neurocomputing 423:301–07. doi:10.1016/j.neucom.2020.10.054.

 Web of Science ®Google Scholar

Gao. (2019). Detecting android malicious applications based on string and function function call graph features. Master’s thesis, BJTU.

 Google Scholar

Lu, X., and , Jiang, F., Zhou, X., Yi, S., Sha, J., Pietro, L. 2019. ASSCA: API sequence and statistics features combined architecture for malware detection. Computer Networks 157:99–111. doi:10.1016/j.comnet.2019.04.007.

 Web of Science ®Google Scholar

Yung C.-H., and Juang W.-S. 2017. Static and dynamic integrated analysis scheme for android malware. Journal of Electronic Science and Technology. doi:10.11989/JEST.1674-862X.60804053.

 Google Scholar

Chen, S., M. Xue, Z. Tang, L. Xu, and H. Zhu. (2016). StormDroid: A streaminglized machine learning-based system for detecting android malware. In Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security, pp. 377–388. Xi'an, CN: ACM.

 Google Scholar

Bai, H., Xie, N., X. Di, and Q. Ye. 2020. FAMD: A fast multifeature android malware detection framework, design, and implementation. IEEE Access 8:194729–40. doi:10.1109/ACCESS.2020.3033026.

 Google Scholar

Xu, L., Zhang, D., Jayasena N., and J. Cavazos. 2018. HADM: hybrid analysis for detection of malware Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016 London, UK. 16:702–24.

 Google Scholar

Pang, Y., Peng, L., Z. Chen, Yang, B., and Zhang H. 2019. Imbalanced learning based on adaptive weighting and Gaussian function synthesizing with an application on Android malware detection. Information Sciences 484:95–112. doi:10.1016/j.ins.2019.01.065.

 Web of Science ®Google Scholar

Qiu J., Zhang J., Luo W., L. Pan, S. Nepal, Y. Wang, and Y. Xiang. 2019. A3CM: automatic capability annotation for android malware. IEEE Access 7 147156–168 doi:10.1109/ACCESS.2019.2946392 .

 Web of Science ®Google Scholar

Yerima S. Y., and Sezer S. 2019. DroidFusion: A novel multilevel classifier fusion approach for Android malware detection. IEEE Transactions on Cybernetics 49 (2):453–66. doi:10.1109/TCYB.2017.2777960.

 PubMed Web of Science ®Google Scholar

Naway, A., and W. Li. (2019). Android malware detection using autoencoder.

 Google Scholar

Alam, S., and Alharbi S. A., Yildirim, S. 2020. Mining nested flow of dominant APIs for detecting android malware. Computer Networks 167:107026. doi:10.1016/j.comnet.2019.107026.

 Web of Science ®Google Scholar

Li, J., Wang, Z., T. Wang, J. Tang, Yang, Y., and Zhou Y. 2018. An android malware detection system based on feature fusion. Chinese Journal of Electronics 27 (6):1206–13. doi:10.1049/cje.2018.09.008.

 Web of Science ®Google Scholar

Fatima, A., Maurya, R., M. S. Dutta, Burget, R., and Masek J. (2019). Android malware detection using genetic algorithm based optimized feature selection and machine learning. 2019 42nd International Conference on Telecommunications and Signal Processing, Budapest, Hungary, TSP 2019, 220–23.

 Google Scholar

Cai, L., Li, Y., and Xiong Z. 2021. JOWMDroid: Android malware detection based on feature weighting with joint optimization of weight-mapping and classifier parameters. Computers and Security 100:102086. doi:10.1016/j.cose.2020.102086.

 Web of Science ®Google Scholar

Kim, T., Kang, B., M. Rho, Sezer, S., and E. G. Im. 2018. A multimodal deep learning method for android malware detection using various features. IEEE Transactions on Information Forensics and Security PP:1–1, 08.

 Google Scholar

Li, Y., Jang, J., Hu, X., Ou, X. (2017). Android malware clustering through malicious payload mining. International symposium on research in attacks, intrusions, and defenses Atlanta, GA. Springer, Cham, 2017. 192–214.

 Google Scholar

Bakour, and Ünver. 2021. DeepVisDroid: Android malware detection by hybridizing image-based features with deep learning techniques. Neural Computing and Applications 33(18):11499–516. 2021. doi:10.1007/s00521-021-05816-y.

 Web of Science ®Google Scholar

Fan, M., Liu, J., X. Luo, Chen, K., Z. Tian, Zheng, Q., and T. Liu. 2018. Android malware familial classification and representative sample selection via frequent subgraph analysis. IEEE Transactions on Information Forensics and Security 13 (8):1890–905. doi:10.1109/TIFS.2018.2806891.

 Web of Science ®Google Scholar

Yen Y.-S., and Sun H.-M. 2019. An Android mutation malware detection based on deep learning using visualization of importance from codes. Microelectronics Reliability 93 (October 2018):109–14. doi:10.1016/j.microrel.2019.01.007.

 Google Scholar

Mercaldo, and Santone. 2021. Audio signal processing for Android malware detection and family identification. Journal of Computer Virology and Hacking Techniques 17 (2):139–52. doi:10.1007/s11416-020-00376-6.

 Web of Science ®Google Scholar

Ünver, H. M., and K. Bakour. 2020. Android malware detection based on image-based features and machine learning techniques. SN Applied Sciences 2 (7):1299. doi:10.1007/s42452-020-3132-2.

 Web of Science ®Google Scholar

Vasan, D., Alazab, M., S. Wassan, Naeem, H., Safaei B., and Zheng Q. 2020. IMCFN: Image-based malware classification using fine-tuned convolutional neural network architecture. Computer Networks 171 (April 2019):107138. doi:10.1016/j.comnet.2020.107138.

 Google Scholar

Dash, and Liu. 2003. Consistency-based search in feature selection. Artificial Intelligence 151 (1–2):155–76. doi:10.1016/S0004-3702(03)00079-1.

 Web of Science ®Google Scholar

Yerima, S. Y., S. Sezer, and G. McWilliams. 2014. Analysis of Bayesian classification-based approaches for android malware detection. IET Information Security 8 (1):25–36. doi:10.1049/iet-ifs.2013.0095.

 Web of Science ®Google Scholar

Spolar, N., Cherman, E. A., Monard M. C., and Lee H. D. (2013). Relieff for multi-label feature selection. In Proceedings of the 2013 Brazilian Conference on Intelligent Systems Fortaleza, Brazil.

 Google Scholar

Ye J.-X., and Gong X.-L. 2010. A novel fast wrapper for feature subset selection. Journal of Changsha University of Science & Technology(Natural Science) 7 69–73 .

 Google Scholar

Witten I. H., and Frank E. 2011. Data mining: Practical machine learning tools and techniques. Acm Sigmod Record 31 (1):76–77. doi:10.1145/507338.507355.

 Google Scholar

Saracino, A., Sgandurra, D., Dini G., and Martinelli F. 2018. MADAM: effective and efficient behavior-based android malware detection and prevention. IEEE Transactions on Dependable and Secure Computing 15 (1):83–97. doi:10.1109/TDSC.2016.2536605.

 Web of Science ®Google Scholar

Sihwail, R., Omar, K., and Ariffin K. A. Z. 2018. A Survey on Malware Analysis Techniques: Static, Dynamic, Hybrid and Memory Analysis. International Journal on Advanced Science, Engineering and Information Technology 8 (4–2):1662–71. doi:10.18517/ijaseit.8.4-2.6827.

 Google Scholar

Rehman, Z.-U., Khan, S. N., K. Muhammad, Lee, J. W., Z. Lv, S. W. Baik, P. A. Shah, K. Awan, and I. Mehmood. 2018. Machine learning-assisted signature and heuristic-based detection of malwares in Android devices. Computers and Electrical Engineering 69:828–41. doi:10.1016/j.compeleceng.2017.11.028.

 Web of Science ®Google Scholar

Li, Zhang, Che, Guo, and Cai. 2021. A survey on feature extraction methods of heuristic malware detection. Journal of Physics: Conference Series 1757 (1):012071.

 Google Scholar

Firdausi, I., Lim, C., Erwin A., and Nugroho A. S. (2010). Analysis of machine learning techniques used in behavior-based malware detection. In Proceedings - 2010 2nd International Conference on Advances in Computing, Control and Telecommunication Technologies, ACT 2010, Washington, DC, 201–03.

 Google Scholar

Alazab, M., Alazab, M., Shalaginov, A., Mesleh A., and Awajan A. 2020. Intelligent mobile malware detection using permission requests and API calls. Future Generation Computer Systems 107:509–21. doi:10.1016/j.future.2020.02.002.

 Web of Science ®Google Scholar

Talha, K. A., Alper, D. I., and Aydin C. 2015. APK auditor: permission-based android malware detection system. Digital Investigation 13:1–14. doi:10.1016/j.diin.2015.01.001.

 Web of Science ®Google Scholar

Priya P. D., and Visalakshi P. 2020. Detecting android malware using an improved filter based technique in embedded software. Microprocessors and Microsystems 76 doi:10.1016/j.micpro.2020.103115.

 Web of Science ®Google Scholar

Chen, Li, Wang, S. Wen, J. Zhang, S. Nepal, Y. Xiang, and K. Ren. 2018. Android HIV: A study of repackaging malware for evading machine-learning detection. arXiv 15:987–1001.

 Google Scholar

Pektaş A., and Acarman T. 2020a. Deep learning for effective Android malware detection using API call graph embeddings. Soft Computing 24 (2):1027–43. doi:10.1007/s00500-019-03940-5.

 Web of Science ®Google Scholar

Pektaş A., and Acarman T. 2020b. Learning to detect Android malware via opcode sequences. Neurocomputing 396:599–608. 2020. doi:10.1016/j.neucom.2018.09.102.

 Web of Science ®Google Scholar

Hasegawa, C. Iyatomi, H. (2018). One-dimensional convolutional neural networks for Android malware detection. In Proceedings - 2018 IEEE 14th International Colloquium on Signal Processing and its Application Penang, Malaysia, CSPA 2018.

 Google Scholar

Mantoo B. A. (2020). A hybrid approach with intrinsic feature-based android malware detection using lda and machine learning. In The International Conference on Recent Innovations in Computing Jammu, India, 295–306. Springer.

 Google Scholar

Firdaus, Anuar, A., Karim N. B., and Razak. 2018. Discovering optimal features using static analysis and a genetic search based method for android malware detection. Frontiers of Information Technology & Electronic Engineering 19 (6):712–36. doi:10.1631/FITEE.1601491.

 Web of Science ®Google Scholar

Taheri, R., Javidan, R., M. Shojafar, Pooranian, Z., A. Miri, and M. Conti. 2020. On defending against label flipping attacks on malware detection systems. Neural Computing and Applications 32 14781–800 doi:10.1007/s00521-020-04831-9.

 Web of Science ®Google Scholar

Chen, Zhang, Yang, and Sahita. (2017). Poster: semi-supervised classification for dynamic android malware detection. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, USA, 2479–81.

 Google Scholar

Atzeni, A., Díaz, F., Marcelli, Sánchez, Squillero, and Tonda. 2018. Countering android malware: A scalable semi-supervised approach for family-signature generation. IEEE Access 6:59540–56. doi:10.1109/ACCESS.2018.2874502.

 Web of Science ®Google Scholar

Mahdavifar, S., Kadir, A. F. A., R. Fatemi, Alhadidi, D., and Ghorbani A. A. (2020). Dynamic android malware category classification using semi-supervised deep learning. In 2020 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress Calgary, AB, 515–22. IEEE.

 Google Scholar

Ribeiro, J., Saghezchi, F. B., G. Mantas, Rodriguez, J., Shepherd, and Abd-Alhameed R. A. 2020. An autonomous host-based intrusion detection system for android mobile devices. Mobile Networks and Applications 25 (1):164–72. doi:10.1007/s11036-019-01220-y.

 Web of Science ®Google Scholar

Fan, M., Luo, X., J. Liu, M. Wang, Nong, C., Zheng Q., and T. Liu. (2019). Graph embedding based familial analysis of android malware using unsupervised learning. In 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE) Montreal, Quebec, 771–82. IEEE.

 Google Scholar

Wen L., and Yu H. 2017. An android malware detection system based on machine learning. AIP Conference Proceedings 1864:020136 doi:10.1063/1.4992953. AIP Publishing LLC.

 Google Scholar

Tiwari S. R., and Shukla R. U. (2018). An android malware detection technique using optimized permission and api with pca. In 2018 Second International Conference on Intelligent Computing and Control Systems Madurai, India, 2611–16 doi:10.1109/ICCONS.2018.8662939. IEEE.

 Google Scholar

Singh, S., Gera, T., F. Ali, D. Thakur, K. Singh, and K.-S. Kwak. 2021. Understanding research trends in android malware research using information modelling techniques. CMC-COMPUTERS MATERIALS & CONTINUA 66 (3):2655–70. doi:10.32604/cmc.2021.014504.

 Web of Science ®Google Scholar

Zhang, W., Ren, H., Jiang Q., and K. Zhang. (2015). Exploring feature extraction and elm in malware detection for android devices. In International Symposium on Neural Networks Jeju, KOR, 489–98 doi:10.1007/978-3-319-25393-0_54. Springer.

 Google Scholar

Fang, Wang, and Geng, Kan. 2019. Feature selection for malware detection based on reinforcement learning. IEEE Access 7:176177–87. doi:10.1109/ACCESS.2019.2957429.

 Google Scholar

Rathore, H., Sahay, S. K., Nikam P., and Sewak M. 2020. Robust android malware detection system against adversarial attacks using q-learning. Information Systems Frontiers 1–16. doi:10.1007/s10796-020-10083-8.

 PubMed Web of Science ®Google Scholar

Khowaja, S., and P. Khuwaja. 2021. Q-learning and lstm based deep active learning strategy for malware defense in industrial iot applications. Multimedia Tools and Applications 1–27. doi:10.1007/s11042-020-10371-0.

 PubMed Web of Science ®Google Scholar

Ham H.-S., -H.-H. Kim, M.-S. Kim, M.-J. Choi, and . 2014. Linear svm-based android malware detection for reliable iot services. Journal of Applied Mathematics 2014:1–10. doi:10.1155/2014/594501.

 Google Scholar

Zhang, X., Marwah, M., Lee I., M. Arlitt, and Goldwasser. 2019. Arlitt. An anomaly contribution explainer for cyber-security applications. . https://arxiv.org/abs/1912.00314v1

 Google Scholar

Faiz, M. F. I., Hussain, M. A., and Marchang N. (2020). Android malware detection using multi-stage classification models. In Conference on Complex, Intelligent, and Software Intensive Systems Lodz, PL, 244–54. Springer.

 Google Scholar

Lashkari, A. H., Kadir, Taheri, and Ghorbani. (2018). Toward developing a systematic approach to generate benchmark android malware datasets and classification. In 2018 International Carnahan Conference on Security Technology (ICCST) Montreal, QC, 1–7. IEEE.

 Google Scholar

Murtaz, M., Azwar, H., Ali S. B., and Rehman S. A framework for android malware detection and classification. (2018). In 2018 IEEE 5th International Conference on Engineering Technologies and Applied Sciences (ICETAS) Bangkok, Thailand, 1–5. IEEE.

 Google Scholar

McLaughlin, N., Rincon, J. M., B. Kang, Yerima, S., P. Miller, Sezer, S., Y. Safaei, Trickel, E., Z. Zhao, Doupé, A. et al, et al. (2017). Deep android malware detection. In Proceedings of the Seventh ACM on Conference on Data and Application Security and Privacy Scottsdale, AZ, 301–08.

 Google Scholar

Lashkari, Kadir, Gonzalez, Mbah, and Ghorbani. (2017). Towards a network-based framework for android malware detection and characterization. In 2017 15th Annual conference on privacy, security and trust (PST) Calgary, AB, 233–23309. IEEE.

 Google Scholar

Nisa, M., Shah, J. H., S. Kanwal, Raza, M., M. A. Khan, Damaševičius, R., and Blažauskas T. 2020. Hybrid malware classification method using segmentation-based fractal texture analysis and deep convolution neural network features. Applied Sciences 10 (14):4966. doi:10.3390/app10144966.

 Google Scholar

Zhu, H.-J., You, Z.-H., Z.-X. Zhu, Shi, W.-L., X. Chen, and L. Cheng. 2018. Droiddet: Effective and robust detection of android malware using static analysis along with rotation forest model. Neurocomputing 272:638–46. doi:10.1016/j.neucom.2017.07.030.

 Web of Science ®Google Scholar

Ilham, S., Abderrahim, G., and Abdelhakim B. A. (2018). Clustering android applications using k-means algorithm using permissions. In The Proceedings of the Third International Conference on Smart City Applications Tétouan, Morocco, 678–90. Springer.

 Google Scholar

Biggio, Nelson, and Laskov. 2013. Poisoning attacks against support vector machines. Computer Science 28:331–44. doi:10.1007/s00450-013-0251-7.

 Google Scholar

Gu T., Dolan-Gavitt B., and Garg S. 2019. Badnets: Identifying vulnerabilities in the machine learning model supply chain. . https://arxiv.org/abs/1708.06733

 Google Scholar

Liu Y., S. Ma, Y. AaFer, W. C. Lee, and X. Zhang. 2018. Trojaning attack on neural networks Network and Distributed System Security Symposium San Diego, CA.

 Google Scholar

Kurakin, A., Goodfellow, I., and Bengio S. (2019). Adversarial examples in the physical world. . https://arxiv.org/abs/1607.02533v4

 Google Scholar

Carlini N., and Wagner D. 2017. Towards evaluating the robustness of neural networks 2017 IEEE Symposium on Security and Privacy (SP) San Jose, CA. 39–57 doi:10.1109/SP.2017.49.

 Google Scholar

Papernot, and Nicolas. (2018). Characterizing the limits and defenses of machine learning in adversarial settings. PhD thesis, The Pennsylvania State University.

 Google Scholar