You are on page 1of 2

Fig. 4.

Comparison analysis of various ML models


[4] [5] Sengupta, J., Ruj, S. and Bit, S.D., 2020. A comprehensive survey
on attacks, security issues and blockchain solutions for IoT and IIoT.
V. CONCLUSION Journal of Network and Computer Applications, 149, p.102481.
We provide an unsupervised learning model that can [5] [6] Ramana, Kadiyala, A. Revathi, A. Gayathri, Rutvij H. Jhaveri, CV
Lakshmi Narayana, and B. Naveen Kumar. "WOGRU-IDS—An
transform an unlabelled network dataset into a labelled one, intelligent intrusion detection system for IoT assisted Wireless Sensor
which can then be used to predict new/unknown attacks. The Networks." Computer Communications 196 (2022): 195-206.
suggested ensemble learning method tags each unlabeled https://doi.org/10.1016/j.comcom.2022.10.001
dataset before using it to train a deep learning model. The [6] [7] Qureshi, K.N., Rana, S.S., Ahmed, A. and Jeon, G., 2020. A novel
study used four ML models and found that MLP and secure attacks detection framework for smart cities industrial
outperformed the other two deep learning models in internet of things. Sustainable Cities and Society, 61, p.102343.
detecting malicious attacks on an IIoT network. The [7] [8] Srastika, N. Bhandary, S. R. S, P. Honnavalli and S. Eswaran
(2022), “An Enhanced alware Detection A roach using achine
proposed ensemble model uses supervised ensemble learning earning and Feature Selection”, 2022 3rd International Conference
techniques to profile the behavioural features of IIoT traffic on Electronics and Sustainable Communication Systems (ICESC), pp.
emitted by compromised IIoT devices. Moreover, the N- 909-914, https://doi.org/10.1109/ICESC54411.2022.9885509.
BaIoT-2021 dataset was used to evaluate the proposed [8] [9] Abosata, N., Al-Rubaye, S., Inalhan, G. and Emmanouilidis, C.,
model's ability to accurately replicate the dynamics of real- 2021. Internet of things for system integrity: A comprehensive survey
world IoT networks. The empirical findings showed that the on security, attacks and countermeasures for industrial applications.
Sensors, 21(11), p.3654.
proposed model outperformed the competition, with a
[9] [10] Aydogan, E., Yilmaz, S., Sen, S., Butun, I., Forsström, S. and
detection accuracy of 99%. To provide real-time botnet Gidlund, M., 2019, May. A central intrusion detection system for rpl-
identification for IoT networks, it has been recommended based industrial internet of things. In 2019 15th IEEE International
that the proposed model be implemented on real-world IoT Workshop on Factory Communication Systems (WFCS) (pp. 1-5).
gateway devices in future studies. Along with such a IEEE.
deployment, research into the various challenges posed by [10] [11] Vatambeti, R., Divya, N.S., Jalla, H.R., Gopalachari, M.V.
low-power IoT nodes may be conducted. These challenges “Attack detection using a lightweight blockchain based elliptic curve
digital signature algorithm in cyber systems”, International Journal of
include, but are not limited to, power consumption, memory Safety and Security Engineering, Vol. 12, No.6, pp. 745-753, 2022
footprint, and communication complexity.
[11] [12] Wang, X., Hu, J., Lin, H., Garg, S., Kaddoum, G., Piran, M.J.
and Hossain, M.S., 2021. QoS and privacy-aware routing for 5G-
REFERENCES enabled industrial internet of things: a federated reinforcement
[1] [1] Shah, Y. and Sengupta, S., 2020, October. A survey on learning approach. IEEE Transactions on Industrial
Classification of Cyber-attacks on IoT and IIoT devices. In 2020 11th Informatics, 18(6), pp.4189-4197.
IEEE Annual Ubiquitous Computing, Electronics & Mobile [12] [13] Biradar, V. G. , Nagaraj, H., Mohan, S., & Pareek, P. K. (2022).
Communication Conference (UEMCON) (pp. 0406-0413). IEEE. Industrial Fluids Components Health Management Using Deep
[2] [2] Nayak, S., Ahmed, N. and Misra, S., 2021. Deep learning-based Learning. In (Ed.), Artificial Neural Networks - Recent Advances,
reliable routing attack detection mechanism for industrial Internet of New Perspectives and Applications . IntechOpen.
Things. Ad Hoc Networks, 123, p.102661. https://doi.org/10.5772/intechopen.107929
[3] [3] Xiong, Z., Wang, H., Zhang, L., Fan, T. and Shen, J., 2020. A [13] [14] Yao, H., Gao, P., Zhang, P., Wang, J., Jiang, C. and Lu, L., 2019.
ring-based routing scheme for distributed energy resources Hybrid intrusion detection system for edge-based IIoT relying on
management in IIoT. IEEE Access, 8, pp.167490-167503. machine-learning-aided detection. IEEE Network, 33(5), pp.75-81.
[4] S. Sanjith, E. Sivaraman and P. B. Honnavalli (2019). Runtime [14] [15] Golchha, R., Joshi, A. and Gupta, G.P., 2023. Voting-based
Malware Detection using hardware features. 10th International Conference Ensemble Learning approach for Cyber Attacks Detection in
on Computing, Communication and Networking Technologies, pp. 1-7, Industrial Internet of Things. Procedia Computer Science, 218,
https://doi.org/10.1109/ICCCNT45670.2019.8944510 . pp.1752-1759.
[15] [16] Sharma, P., Sakthivel, T. and Alnajjar, I.A., 2023. Optimized [21] [22] Reddy, K. Uday Kumar, S. Shabbiha, and M. Rudra Kumar.
Federated Learning with Ensemble of Sequential Models for "Design of high security smart health care monitoring system using
Detecting RPL Routing Attacks for AMI Networks. IoT." Int. J 8 (2020).
[16] [17] Rashid, M.M., Khan, S.U., Eusufzai, F., Redwan, M.A., Sabuj, [22] [23] Abbasi, F., Naderan, M. and Alavi, S.E., 2021, May. Anomaly
S.R. and Elsharief, M., 2023. A Federated Learning-Based Approach detection in Internet of Things using feature selection and
for Improving Intrusion Detection in Industrial Internet of Things classification based on Logistic Regression and Artificial Neural
Networks. Network, 3(1), pp.158-179. Network on N-BaIoT dataset. In 2021 5th International Conference
[17] [18] Nagarajan, S., Kayalvizhi, S., Subhashini, R. and Anitha, V., on Internet of Things and Applications (IoT) (pp. 1-7). IEEE.
2023. Hybrid Honey Badger-World Cup Algorithm-based Deep [23] [24] V. Kishen Ajay Kumar, M. Rudra Kumar, N. Shribala, Ninni
Learning for Malicious Intrusion Detection in Industrial Control Singh, Vinit Kumar Gunjan, Kazy Noor-e-alam Siddiquee,
Systems. Computers & Industrial Engineering, p.109166. Muhammad Arif, "Dynamic Wavelength Scheduling by
[18] [19] Alazab, A., Khraisat, A., Singh, S., Bevinakoppa, S. and Mahdi, Multiobjectives in OBS Networks", Journal of Mathematics, vol.
O.A., 2023. Routing Attacks Detection in 6LoWPAN-Based Internet 2022, Article ID 3806018, 10 pages, 2022.
of Things. Electronics, 12(6), p.1320. https://doi.org/10.1155/2022/3806018
[19] [20] Abosata, N., Al-Rubaye, S. and Inalhan, G., 2023. Customised [24] [25] Rudra Kumar, M., Gunjan, V.K. (2022). Peer Level Credit
Intrusion Detection for an Industrial IoT Heterogeneous Network Rating: An Extended Plugin for Credit Scoring Framework. In:
Based on Machine Learning Algorithms Called FTL-CID. Sensors, Kumar, A., Mozar, S. (eds) ICCCE 2021. Lecture Notes in Electrical
23(1), p.321. Engineering, vol 828. Springer, Singapore.
https://doi.org/10.1007/978-981-16-7985-8_128
[20] [21] K. Ramana et al., "A Vision Transformer Approach for Traffic
Congestion Prediction in Urban Areas," in IEEE Transactions on [25] [26] Al-Haija, Q.A.; Smadi, A.A.; Allehyani, M.F. Meticulously
Intelligent Transportation Systems, vol. 24, no. 4, pp. 3922-3934, Intelligent Identification System for Smart Grid Network Stability to
April 2023, doi: 10.1109/TITS.2022.3233801 Optimize Risk Management. Energies 2021, 14, 6935.

You might also like