Anomaly Detection for Cyber Internet of Things Attacks: A Systematic Review

Figures & data

Table 1. Search terms and their results.

Sr.	Search Terms	Operators	IEEE	Springer	ACM	Science Direct	Taylor & Francis
1	Data Preprocessing	AND	1299	10,366	476	14,584	1214
2	Data Preprocessing IoT	AND	30	462	41	1178	35
3	Data Preprocessing on IoT Datasets	AND	6	319	24	751	21
4	Data Preprocessing on IoT Datasets Anomaly	AND	1	75	7	229	6
5	Data Preprocessing on IoT Datasets for Anomaly detection	AND	1	73	7	197	6

Figure 1. Search process.

Table 2. Data extraction.

Sr.	Description	Details
1	Criteria	Title, year, type (journal), abstract, publisher
Extraction of Data
Overview	Whether aims and goals of our selected study are according to our criteria?
Methods	Which qualitative and quantitative methods are used in selected study?
Results	What are the results of selected study?
Datasets	Which datasets are used?
Validation	Validate the techniques from selected researches.
Synthesis of Data
Techniques	Which techniques are used for data preprocessing of IoT datasets?

Summary.

Figure 2. Publication based on leading journals.

Figure 3. Publication based on scientific database.

Figure 4. Data preprocessing technique.

Figure 5. Extracted datasets of IoT.

Figure 6. Extracted model/method.

Figure 7. Extracted performance metrics of IoT.

Table 3. Number of selected features against research identification.

Sr.	No. of Selected Features	Research Identification
1.	6 features	Kaur et al. (2019)
2.	19,41 features	Aljawarneh and Vangipuram (2018)
3.	41 features	Bhatia and Sood (2017)
4.	13 features	Fisher et al. (2018)
5.	9 features	Hasan et al. (2019)
6.	42 features	Rathore and Park (2018)
7.	20 features	Sun et al. (2019)

Table 4. Relationship of identification research with respect to SLR.

Sr.	Model/Method	Research Identification	Preprocessing Techniques	Performance Metric	Dataset
1.	Machine learning based	Kaur et al. (2019)	✓	✓	✓
2.	M/M/1 queuing model, Map Reduce Mechanism	Babar and Arif (2017)	✓		✓
3.	Artificial Neural Network (ANN) model	Al-Makhadmeh and Tolba (2019); Bhatia and Sood (2017), Kale and Sonavane (2019)	✓ ✓ ✓	✓ ✓ ✓	✓
4.	Deep learning Model	Diro and Chilamkurti (2018), Zhang et al. (2018); Tong et al. (2018); Lin et al. (2017)	✓ ✓ ✓ ✓	✓ ✓	✓ ✓ ✓ ✓
5.	Markov model	Fisher et al. (2018)		✓	✓
6.	Naive Bayes methods	Mehmood et al. (2018)	✓	✓	✓
7.	Substantial outlier detection framework	Nesa, Ghosh, and Banerjee (2018)	✓	✓	✓
8.	ELM classifier and semi-supervised Fuzzy C-Means	Rathore and Park (2018)	✓	✓	✓
9.	Method based on random forest learning	Sarker and Salah (2019)	✓	✓	✓
10.	Framework based on graph-based clustering algorithm and bayesian probabilistic graphical model	Sun et al. (2019)	✓		✓
11.	Deep learning and edge-based computing	Wang et al. (2019b)		✓	✓
12.	Sequential load forecasting model based on RNNs and LSTM	Han et al. (2020)	✓	✓	✓
13.	CNN and LSTM-based autoencoder	Yin et al. (2020)	✓	✓	✓
14.	Semisupervised adversarial learning method SaliencyGAN	Wang et al. (2019a)		✓	✓
15.	Deep Model Compression (DNN)	Bhattacharya et al. (2020)
16.	SeqGAN-GABP, SeqGAN-Elman algorithm	Geng and Du (2020)	✓	✓
17.	Autoencoder Networks	Demertzis et al. (2020)	✓	✓
18.	Multi-layer perceptron model	Hosseinzadeh et al. (2020)	✓	✓	✓
19.	Long Short-Term Memory with RNN	Xu et al. (2020)
20.	ADE-IoT attack detection framework	Baig et al. (2020)	✓	✓	✓
21.	Machine learning classifiers	Karanja, Masupe, and Jeffrey (2020)	✓	✓	✓
22.	Deep neural network (DNN)	RM et al. (2020)	✓	✓
23.	CNN-based deep learning	Jung et al. (2020)	✓	✓	✓
24.	Particle deep framework (PDF)	Koroniotis, Moustafa, and Sitnikova (2020)	✓	✓	✓
25.	Itr-MS-STLecImp	Liu et al. (2020)			✓
26.	Convolution neural network	Shi et al. (2020)		✓	✓

Kaur, M., G. Kaur, P. K. Sharma, A. Jolfaei, and D. Singh. 2019. Binary cuckoo search metaheuristic-based supercomputing framework for human behavior analysis in smart home. The Journal of Supercomputing 76 (4):1–24. doi:10.1007/s11227-019-02998-0.

 Web of Science ®Google Scholar

Aljawarneh, S. A., and R. Vangipuram. 2018. GARUDA: Gaussian dissimilarity measure for feature representation and anomaly detection in Internet of things. The Journal of Supercomputing 76 (6):1–3263. doi:10.1007/s11227-018-2397-3.

 Web of Science ®Google Scholar

Bhatia, M., and S. K. Sood. 2017. A comprehensive health assessment framework to facilitate IoT-assisted smart workouts: A predictive healthcare perspective. Computers in Industry 92:50–66. doi:10.1016/j.compind.2017.06.009.

 Web of Science ®Google Scholar

Fisher, P. S., J. James, J. Baek, and C. Kim. 2018. Mining intelligent solution to compensate missing data context of medical IoT devices. Personal and Ubiquitous Computing 22 (1):219–24. doi:10.1007/s00779-017-1106-1.

 Web of Science ®Google Scholar

Hasan, M., M. M. Islam, M. I. I. Zarif, and M. M. A. Hashem. 2019. Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches. Internet of Things. 7:100059. doi:10.1016/j.iot.2019.100059.

 Google Scholar

Rathore, S., and J. H. Park. 2018. Semi-supervised learning based distributed attack detection framework for IoT. Applied Soft Computing 72:79–89. doi:10.1016/j.asoc.2018.05.049.

 Web of Science ®Google Scholar

Sun, P., J. Li, M. Z. Alam Bhuiyan, L. Wang, and B. Li. 2019. Modeling and clustering attacker activities in IoT through machine learning techniques. Information Sciences 479:456–71. doi:10.1016/j.ins.2018.04.065.

 Web of Science ®Google Scholar

Babar, M., and F. Arif. 2017. Smart urban planning using big data analytics to contend with the interoperability in internet of things. Future Generation Computer Systems 77:65–76. doi:10.1016/j.future.2017.07.029.

 Web of Science ®Google Scholar

Al-Makhadmeh, Z., and A. Tolba. 2019. Utilizing IoT wearable medical device for heart disease prediction using higher order Boltzmann model: A classification approach. Measurement 147:106815. doi:10.1016/j.measurement.2019.07.043.

 Web of Science ®Google Scholar

Kale, A. P., and S. P. Sonavane. 2019. IoT based smart farming: Feature subset selection for optimized high-dimensional data using improved GA based approach for ELM. Computers and Electronics in Agriculture 161:225–32. doi:10.1016/j.compag.2018.04.027.

 Web of Science ®Google Scholar

Diro, A. A., and N. Chilamkurti. 2018. Distributed attack detection scheme using deep learning approach for internet of things. Future Generation Computer Systems 82:761–68. doi:10.1016/j.future.2017.08.043.

 Web of Science ®Google Scholar

Ray, P. P. 2018. A survey on internet of things architectures. Journal of King Saud University-Computer and Information Sciences 30 (3):291–319. doi:10.1016/j.jksuci.2016.10.003.

 Web of Science ®Google Scholar

Tong, C., X. Yin, S. Wang, and Z. Zheng. 2018. A novel deep learning method for aircraft landing speed prediction based on cloud-based sensor data. Future Generation Computer Systems 88:552–58. doi:10.1016/j.future.2018.06.023.

 Web of Science ®Google Scholar

Lin, P., D.-C. Lyu, F. Chen, S.-S. Wang, and Y. Tsao. 2017. Multi-style learning with denoising autoencoders for acoustic modeling in the internet of things (IoT). Computer Speech & Language 46:481–95. doi:10.1016/j.csl.2017.02.001.

 Web of Science ®Google Scholar

Mehmood, A., M. Mukherjee, S. H. Ahmed, H. Song, and K. M. Malik. 2018. NBC-MAIDS: Naïve bayesian classification technique in multi-agent system-enriched IDS for securing IoT against DDoS attacks. The Journal of Supercomputing 74 (10):5156–70. doi:10.1007/s11227-018-2413-7.

 Web of Science ®Google Scholar

Nesa, N., T. Ghosh, and I. Banerjee. 2018. Non-parametric sequence-based learning approach for outlier detection in IoT. Future Generation Computer Systems 82:412–21. doi:10.1016/j.future.2017.11.021.

 Web of Science ®Google Scholar

Sarker, I. H., and K. Salah. 2019. Appspred: Predicting context-aware smartphone apps using random forest learning. Internet of Things 8:100106. doi:10.1016/j.iot.2019.100106.

 Google Scholar

Wang, T., S. Li, and B. Hannaford. 2019b. A model-based recurrent neural network with randomness for efficient control with applications. IEEE Transactions on Industrial Informatics 15 (4):2054–63. doi:10.1109/TII.2018.2869588.

 PubMed Web of Science ®Google Scholar

Han, T., et al. 2020. An efficient deep learning framework for intelligent energy management in IoT networks. IEEE Internet of Things Journal. 8 5: 3170–3179. 10.1109/JIOT.2020.3013306

 Web of Science ®Google Scholar

Yin, C., Zhang, S., Wang, J., & Xiong, N. N. 2020. Anomaly detection based on convolutional recurrent autoencoder for IoT time series. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(1), 112–122.

 Google Scholar

Wang, C., S. Dong, X. Zhao, G. Papanastasiou, H. Zhang, and G. Yang. 2019a. Saliencygan: Deep learning semisupervised salient object detection in the fog of iot. IEEE Transactions on Industrial Informatics 16 (4):2667–76. doi:10.1109/TII.2019.2945362.

 Web of Science ®Google Scholar

Bhattacharya, S., D. Manousakas, A. G. C. P. Ramos, S. I. Venieris, N. D. Lane, and C. Mascolo. 2020. Countering acoustic adversarial attacks in microphone-equipped smart home devices. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4 (2):1–24. doi:10.1145/3397332.

 PubMedGoogle Scholar

Geng, T., and Y. Du. 2020. The business model of intelligent manufacturing with internet of things and machine learning. Enterprise Information Systems 1–19.

 Google Scholar

Demertzis, K., L. Iliadis, N. Tziritas, and P. Kikiras. 2020. Anomaly detection via blockchained deep learning smart contracts in industry 4.0. Neural Computing & Applications 32 (23):17361–78. doi:10.1007/s00521-020-05189-8.

 Google Scholar

Hosseinzadeh M, Ahmed OH, Ghafour MY, Safara F, Ali S, Vo B, Chiang HS. 2020. A multiple multilayer perceptron neural network with an adaptive learning algorithm for thyroid disease diagnosis in the internet of medical things. The Journal of Supercomputing. 2021 Apr;77(4):3616–37.

 Web of Science ®Google Scholar

Xu, R., Y. Cheng, Z. Liu, Y. Xie, and Y. Yang. 2020. Improved long short-term memory based anomaly detection with concept drift adaptive method for supporting IoT services. Future Generation Computer Systems 112:228–42. doi:10.1016/j.future.2020.05.035.

 Web of Science ®Google Scholar

Baig, Z. A., S. Sanguanpong, S. N. Firdous, T. G. Nguyen, and C. So-In. 2020. Averaged dependence estimators for DoS attack detection in IoT networks. Future Generation Computer Systems 102:198–209. doi:10.1016/j.future.2019.08.007.

 Web of Science ®Google Scholar

Karanja, E. M., S. Masupe, and M. G. Jeffrey. 2020. Analysis of internet of things malware using image texture features and machine learning techniques. Internet of Things 9:100153. doi:10.1016/j.iot.2019.100153.

 Google Scholar

RM, S. P., Maddikunta, P. K. R., Parimala, M., Koppu, S., Gadekallu, T. R., Chowdhary, C. L., & Alazab, M. 2020. An effective feature engineering for DNN using hybrid PCA-GWO for intrusion detection in IoMT architecture. Computer Communications, 160, 139–149.

 Google Scholar

Jung, W., H. Zhao, M. Sun, and G. Zhou. 2020. IoT botnet detection via power consumption modeling. Smart Health 15:100103. doi:10.1016/j.smhl.2019.100103.

 Google Scholar

Koroniotis, N., N. Moustafa, and E. Sitnikova. 2020. A new network forensic framework based on deep learning for internet of things networks: A particle deep framework. Future Generation Computer Systems 110:91–106. doi:10.1016/j.future.2020.03.042.

 Web of Science ®Google Scholar

Liu, Y., T. Dillon, W. Yu, W. Rahayu, and F. Mostafa. 2020. Missing value imputation for industrial IoT sensor data with large gaps. IEEE Internet of Things Journal 7 (8):6855–67. doi:10.1109/JIOT.2020.2970467.

 Web of Science ®Google Scholar

Shi, Y., X. Zhang, Q. Hu, and H. Cheng. 2020. Data recovery algorithm based on generative adversarial networks in crowd sensing internet of things. Personal and Ubiquitous Computing 1–14. doi:10.1007/s00779-020-01428-w.

 PubMed Web of Science ®Google Scholar