# A Classy Multifacet Clustering and Fused Optimization Based Classification Methodologies for SCADA Security

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

- To preprocess and normalize the given IDS dataset by grouping the attributes into the form of clusters, the multifacet data clustering model (MDCM) is implemented, which helps to simplify the process of classification.
- To optimally select the features for increasing the efficiency of classifier training, the gradient descent spider monkey optimization (GDSMO) mechanism is utilized, which minimizes the time of processing and increases the convergence rate.
- To exactly spot the intrusions from the clustered datasets based on the optimal set of features, the deep sequential long short term memory (DS-LSTM) technique is employed.
- To assess the performance of the proposed GDSMO-DSLSTM-based IDS framework, various evaluation measures have been utilized, and the obtained results are compared with other recent IDS approaches.

## 2. Related Works

- Accurate detection
- Improved system reliability
- Reduced false positives
- Ability to handle large dimensional datasets
- Fast processing

- Inability in handling large datasets
- High false positives and error outputs
- Misclassification results
- Requires high time consumption for training data
- Follows complex computational operations for classification

## 3. Proposed Methodology

- Data preprocessing and clustering
- Segmentation
- Feature Optimization
- Attack Prediction

#### 3.1. Data Preprocessing and Clustering

- Attribute normalization
- Distance computation
- Clustering

#### 3.2. Gradient Descent Spider Monkey Optimization (GDSMO)

- Initialization
- Local Leader Selection
- Global Leader Selection
- Learning module
- Decision module

Algorithm 1 Gradient Descent Spider Monkey Optimization (GDSMO) |

$\mathrm{Input}:\hspace{1em}\mathrm{Initial}\mathrm{set}\mathrm{of}\mathrm{population}{s}_{i}\left(a\le i\le m\right)$$,\mathrm{transaction}\mathrm{probability}\tau $$,\mathrm{and}\mathrm{switching}\mathrm{probability}{\alpha}_{p}$; $\mathrm{Output}:\hspace{1em}\mathrm{Best}\mathrm{optimal}\mathrm{solution}Op{t}_{a\left(i\right)}$; $\mathrm{Step}1:\hspace{1em}\mathrm{At}\mathrm{first},\mathrm{the}\mathrm{objective}\mathrm{function}O\left(s\right)$$\mathrm{is}\mathrm{constructed}\mathrm{with}\mathrm{the}\mathrm{set}\mathrm{of}s={\left({s}_{1},{s}_{2}\dots {s}_{d}\right)}^{T}$; $\mathrm{Step}2:\hspace{1em}\mathrm{Initialize}\mathrm{the}\mathrm{set}\mathrm{of}\mathrm{populations}\mathrm{of}\mathrm{k}\mathrm{number}\mathrm{of}\mathrm{spider}\mathrm{monkeys}{s}_{i}$$\mathrm{with}1\le i\le k$$,\mathrm{and}\mathrm{its}\mathrm{switching}\mathrm{probability}{\alpha}_{p}\in \left[0,1\right]$ with the maximum number of iterations; $\mathrm{Step}3:\hspace{1em}\mathrm{While}(lMa{x}_{itr})$ do. Randomly select the spider monkeys for computing the fitness function by using Equations (5)–(7); $\mathrm{Verify}\mathrm{the}\mathrm{value}\mathrm{of}{M}_{i}=O\left({s}_{i}^{l+1}\right)$ for computing the fitness value; $\mathrm{While}\mathrm{the}\mathrm{fitness}\mathrm{of}{s}_{i}$$\mathrm{is}\mathrm{not}\mathrm{at}(lIt{r}_{max})$ do $\mathrm{Split}\mathrm{the}\mathrm{entire}\mathrm{set}\mathrm{of}\mathrm{population}{s}_{i}$$\mathrm{with}1\le i\le n$ into g number of groups; //Local and global leader phase Update the position of monkeys and global leader as shown in Equations (8)–(10); //Learning phase Select the best global leader based on the probability as defined in Equation (11); Update the position of global & local leaders, and compute the fitness value for the leaders; Group members can update their position by using Equation (12); $Itr=Itr+1$; End; $\mathrm{Step}4:\hspace{1em}\mathrm{If}({M}_{i}{M}_{j})$ then ${M}_{j}\leftarrow {M}_{i}$; //Replace the old solution with the new solution; End if; $\mathrm{Step}5:\hspace{1em}\mathrm{If}(rand\left[0,1\right]{\alpha}_{p})$ then Re-initialize the entire population with the group members; Obtain the global best solution; End if; $\mathrm{Step}6:\hspace{1em}\mathrm{If}({M}_{i}{M}_{min})$ //Old solution is replaced with the new solution $Op{t}_{a\left(i\right)}={s}_{i}$; ${M}_{i}={M}_{min}$; //Arrange the most feasible solutions for determining the current best solution;Increment the count l by 1; $\mathrm{Return}\mathrm{the}\mathrm{best}\mathrm{optimal}\mathrm{solution}\mathrm{as}Op{t}_{a\left(i\right)}$; End; |

#### 3.3. Deep Sequential Long Short Term Memory (DS-LSTM) Classification Model

Algorithm 2 Deep Sequential Long Short Term Memory (DS-LSTM) Classification |

Input:$\hspace{1em}\mathrm{Optimal}\mathrm{set}\mathrm{of}\mathrm{features}Op{t}_{a\left(i\right)}$$,\mathrm{learning}\mathrm{model},\mathrm{and}\mathrm{Label}{C}_{U}$; Output:$\hspace{1em}\mathrm{Classified}\mathrm{label}{C}_{O}$; $\mathrm{Step}1:\hspace{1em}\mathrm{Compute}\mathrm{the}\mathrm{deterministic}\mathrm{rules}\Delta {D}_{r}\left(x\right)$$\mathrm{with}\mathrm{respect}\mathrm{to}\mathrm{the}\mathrm{logical}\mathrm{vector}\sigma $$\mathrm{and}\mathrm{featured}\mathrm{data}Op{t}_{a\left(i\right)}$ by using Equation (13); Step 2: Estimate the feature map based on the convolutional operation as shown in Equation (14); Step 3: Compute the trail vector according to the target vector by using Equation (15); $\mathrm{Step}4:\hspace{1em}\mathrm{Based}\mathrm{on}\mathrm{the}\mathrm{obtained}\mathrm{target}\mathrm{vector}\mathrm{and}\mathrm{weight}\mathrm{value},\mathrm{the}\mathrm{dropout}\mathrm{factor}\partial $ is estimated as shown in Equation (16); $\mathrm{Step}5:\hspace{1em}\mathrm{Consequently},\mathrm{the}\mathrm{memory}\mathrm{cells}{m}_{c}$ are updated with the feature map and feedback value as represented in Equation (17); $\mathrm{Step}6:\hspace{1em}\mathrm{The}\mathrm{distributed}\mathrm{probability}Di{P}_{sd}$ function is computed for each class of data by using Equation (18); Step 7: Compute the binary cross entropy for the definite segments as shown in Equation (19); $\mathrm{Step}8:\hspace{1em}\mathrm{Finally},\mathrm{the}\mathrm{output}\mathrm{classified}\mathrm{label}{C}_{O}$ is predicted as represented in Equation (20); |

## 4. Results and Discussions

#### 4.1. Simulation Analysis

#### 4.2. Comparative Analysis

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Upadhyay, D.; Sampalli, S. SCADA (Supervisory Control and Data Acquisition) systems: Vulnerability assessment and security recommendations. Comput. Secur.
**2020**, 89, 101666. [Google Scholar] [CrossRef] - Yadav, G.; Paul, K. Architecture and security of SCADA systems: A review. Int. J. Crit. Infrastruct. Prot.
**2021**, 34, 100433. [Google Scholar] [CrossRef] - Pliatsios, D.; Sarigiannidis, P.; Lagkas, T.; Sarigiannidis, A.G. A survey on SCADA systems: Secure protocols, incidents, threats and tactics. IEEE Commun. Surv. Tutor.
**2020**, 22, 1942–1976. [Google Scholar] [CrossRef] - Suaboot, J.; Fahad, A.; Tari, Z.; Grundy, J.; Mahmood, A.N.; Almalawi, A.; Zomaya, A.Y.; Drira, K. A taxonomy of supervised learning for idss in scada environments. ACM Comput. Surv. (CSUR)
**2020**, 53, 1–37. [Google Scholar] [CrossRef] - el Kalam, A.A. Securing SCADA and critical industrial systems: From needs to security mechanisms. Int. J. Crit. Infrastruct. Prot.
**2021**, 32, 100394. [Google Scholar] [CrossRef] - Rakas, S.V.B.; Stojanović, M.D.; Marković-Petrović, J.D. A review of research work on network-based scada intrusion detection systems. IEEE Access
**2020**, 8, 93083–93108. [Google Scholar] [CrossRef] - Alimi, O.A.; Ouahada, K.; Abu-Mahfouz, A.M.; Rimer, S.; Alimi, K.O.A. A review of research works on supervised learning algorithms for SCADA intrusion detection and classification. Sustainability
**2021**, 13, 9597. [Google Scholar] [CrossRef] - Al-Asiri, M.; El-Alfy, E.-S.M. On using physical based intrusion detection in SCADA systems. Procedia Comput. Sci.
**2020**, 170, 34–42. [Google Scholar] [CrossRef] - Qian, X.; Du, B.; Chen, B.; Qu, K.; Zeng, K.; Liu, J. Cyber-physical integrated intrusion detection scheme in SCADA system of process manufacturing industry. IEEE Access
**2020**, 8, 147471–147481. [Google Scholar] [CrossRef] - Maglaras, L.; Cruz, T.; Ferrag, M.A.; Janicke, H. Teaching the process of building an Intrusion Detection System using data from a small-scale SCADA testbed. Internet Technol. Lett.
**2020**, 3, e132. [Google Scholar] [CrossRef] - Upadhyay, D.; Manero, J.; Zaman, M.; Sampalli, S. Intrusion detection in SCADA based power grids: Recursive feature elimination model with majority vote ensemble algorithm. IEEE Trans. Netw. Sci. Eng.
**2021**, 8, 2559–2574. [Google Scholar] [CrossRef] - Qassim, Q.S.; Jamil, N.; Mahdi, M.N.; Rahim, A.A.A. Towards scada threat intelligence based on intrusion detection systems—A short review. In Proceedings of the 2020 8th International Conference on Information Technology and Multimedia (ICIMU), Selangor, Malaysia, 24–26 August 2020; pp. 144–149. [Google Scholar] [CrossRef]
- Chaithanya, P.; Priyanga, S.; Pravinraj, S.; Sriram, V.S. SSO-IF: An Outlier Detection Approach for Intrusion Detection in SCADA Systems. In Inventive Communication and Computational Technologies; Springer: Berlin/Heidelberg, Germany, 2020; pp. 921–929. [Google Scholar]
- Upadhyay, D.; Manero, J.; Zaman, M.; Sampalli, S. Gradient boosting feature selection with machine learning classifiers for intrusion detection on power grids. IEEE Trans. Netw. Serv. Manag.
**2020**, 18, 1104–1116. [Google Scholar] [CrossRef] - Shitharth, S.; Sangeetha, K.; Kumar, B.P. Integrated probabilistic relevancy classification (prc) scheme for intrusion detection in scada network. In Design Frameworks for Wireless Networks; Springer: Berlin/Heidelberg, Germany, 2020; pp. 41–63. [Google Scholar]
- Gaiceanu, M.; Stanculescu, M.; Andrei, P.C.; Solcanu, V.; Gaiceanu, T.; Andrei, H. Intrusion Detection on ICS and SCADA Networks. In Recent Developments on Industrial Control Systems Resilience; Springer: Berlin/Heidelberg, Germany, 2020; pp. 197–262. [Google Scholar]
- Sangeetha, K.; Shitharth, S.; Mohammed, G.B. Enhanced SCADA IDS Security by Using MSOM Hybrid Unsupervised Algorithm. Int. J. Web-Based Learn. Teach. Technol. (IJWLTT)
**2022**, 17, 1–9. [Google Scholar] [CrossRef] - Rajesh, L.; Satyanarayana, P. Evaluation of Machine Learning Algorithms for Detection of Malicious Traffic in SCADA Network. J. Electr. Eng. Technol.
**2021**, 1–16. [Google Scholar] [CrossRef] - Yin, X.C.; Liu, Z.G.; Nkenyereye, L.; Ndibanje, B. Toward an applied cyber security solution in IoT-based smart grids: An intrusion detection system approach. Sensors
**2019**, 19, 4952. [Google Scholar] [CrossRef] [Green Version] - Yang, H.; Cheng, L.; Chuah, M.C. Deep-learning-based network intrusion detection for SCADA systems. In Proceedings of the 2019 IEEE Conference on Communications and Network Security (CNS), Washington, DC, USA, 10–12 June 2019; pp. 1–7. [Google Scholar]
- Ozkan-Okay, M.; Samet, R.; Aslan, Ö.; Gupta, D. A Comprehensive Systematic Literature Review on Intrusion Detection Systems. IEEE Access
**2021**, 9, 157727–157760. [Google Scholar] [CrossRef] - Khan, I.A.; Pi, D.; Khan, Z.U.; Hussain, Y.; Nawaz, A. HML-IDS: A hybrid-multilevel anomaly prediction approach for intrusion detection in SCADA systems. IEEE Access
**2019**, 7, 89507–89521. [Google Scholar] [CrossRef] - Singh, V.K.; Ebrahem, H.; Govindarasu, M. Security evaluation of two intrusion detection systems in smart grid scada environment. In Proceedings of the 2018 North American Power Symposium (NAPS), Fargo, ND, USA, 9–11 September 2018; pp. 1–6. [Google Scholar]
- Gao, J.; Gan, L.; Buschendorf, F.; Zhang, L.; Liu, H.; Li, P.; Dong, X.; Lu, T. LSTM for SCADA intrusion detection. In Proceedings of the 2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM), Victoria, BC, Canada, 21–23 August 2019; pp. 1–5. [Google Scholar]
- Waagsnes, H.; Ulltveit-Moe, N. Intrusion Detection System Test Framework for SCADA Systems. In Proceedings of the 4th International Conference on Information Systems Security and Privacy (ICISSP 2018), Madeira, Portugal, 22–24 January 2018; pp. 275–285. [Google Scholar]
- Altaha, M.; Lee, J.-M.; Muhammad, A.; Hong, S. An autoencoder-based network intrusion detection system for the SCADA system. J. Commun.
**2021**, 16, 210–216. [Google Scholar] [CrossRef] - Gao, J.; Gan, L.; Buschendorf, F.; Zhang, L.; Liu, H.; Li, P.; Dong, X.; Lu, T. Omni SCADA intrusion detection using deep learning algorithms. IEEE Internet Things J.
**2020**, 8, 951–961. [Google Scholar] [CrossRef] - Tamy, S.; Belhadaoui, H.; Rabbah, M.A.; Rabbah, N.; Rifi, M. An evaluation of machine learning algorithms to detect attacks in SCADA network. In Proceedings of the 2019 7th Mediterranean Congress of Telecommunications (CMT), Fez, Morocco, 24–25 October 2019; pp. 1–5. [Google Scholar]
- Justindhas, Y.; Jeyanthi, P. Attack detection and prevention in IoT-SCADA networks using NK-classifier. Soft Comput.
**2022**, 1–13. [Google Scholar] [CrossRef] - Hopkins, S.; Kalaimannan, E. Towards establishing a security engineered SCADA framework. J. Cyber Secur. Technol.
**2019**, 3, 47–59. [Google Scholar] [CrossRef] - Teixeira, M.A.; Salman, T.; Zolanvari, M.; Jain, R.; Meskin, N.; Samaka, M. SCADA system testbed for cybersecurity research using machine learning approach. Future Internet
**2018**, 10, 76. [Google Scholar] [CrossRef] [Green Version] - Radoglou-Grammatikis, P.; Sarigiannidis, P.; Efstathopoulos, G.; Karypidis, P.-A.; Sarigiannidis, A. DIDEROT: An intrusion detection and prevention system for DNP3-based SCADA systems. In Proceedings of the 15th International Conference on Availability, Reliability and Security, Virtual Event, Coimbra, Portugal, 25–28 August 2020; pp. 1–8. [Google Scholar]
- Benisha, R.; Ratna, S.R. Design of intrusion detection and prevention in SCADA system for the detection of bias injection attacks. Secur. Commun. Netw.
**2019**, 2019, 108248. [Google Scholar] [CrossRef] [Green Version] - Li, H.; Shi, D.; Wang, W.; Liao, D.; Gadekallu, T.R.; Yu, K. Secure Routing for LEO Satellite Network Survivability. Comput. Netw.
**2022**, 109011. [Google Scholar] [CrossRef] - Hariprasath, M.; Subramanian, S.; Ganesan, S.; Abirami, M. Reliable/cost-effective optimization framework for precise phasor measurement locations. Int. J. Power Energy Syst.
**2017**, 37. [Google Scholar] [CrossRef] - Yu, Y.; Rashidi, M.; Samali, B.; Mohammadi, M.; Nguyen, T.N.; Zhou, X. Crack detection of concrete structures using deep convolutional neural networks optimized by enhanced chicken swarm algorithm. Struct. Health Monit.
**2022**. [Google Scholar] [CrossRef] - Gibb, S.; La, H.M.; Louis, S. A genetic algorithm for convolutional network structure optimization for concrete crack detection. In Proceedings of the 2018 IEEE Congress on Evolutionary Computation (CEC), Rio de Janeiro, Brazil, 8–13 July 2018; pp. 1–8. [Google Scholar]
- Agrawal, S.; Sarkar, S.; Alazab, M.; Maddikunta, P.K.R.; Gadekallu, T.R.; Pham, Q.-V. Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning. Comput. Intell. Neurosci.
**2021**, 2021, 7156420. [Google Scholar] [CrossRef] - Selvarajan, S.; Shaik, M.; Ameerjohn, S.; Kannan, S. Mining of intrusion attack in SCADA network using clustering and genetically seeded flora-based optimal classification algorithm. IET Inf. Secur.
**2019**, 14, 1–11. [Google Scholar] [CrossRef] - Bhattacharya, S.; Maddikunta, P.K.R.; Meenakshisundaram, I.; Gadekallu, T.R.; Sharma, S.; Alkahtani, M.; Abidi, M.H. Deep neural networks based approach for battery life prediction. CMC-Comput. Mater. Contin.
**2021**, 69, 2599–2615. [Google Scholar] [CrossRef] - Grammatikis, P.R.; Sarigiannidis, P.; Efstathopoulos, G.; Panaousis, E. ARIES: A novel multivariate intrusion detection system for smart grid. Sensors
**2020**, 20, 5305. [Google Scholar] [CrossRef] - Sheng, C.; Yao, Y.; Fu, Q.; Yang, W. A cyber-physical model for SCADA system and its intrusion detection. Comput. Netw.
**2021**, 185, 107677. [Google Scholar] [CrossRef] - Ferrag, M.A.; Maglaras, L.; Moschoyiannis, S.; Janicke, H. Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. J. Inf. Secur. Appl.
**2020**, 50, 102419. [Google Scholar] [CrossRef]

**Figure 11.**(

**a**). Accuracy with respect to best iterations and (

**b**). F1-score with respect to best iterations.

**Figure 16.**Performance analysis of existing and proposed classification approaches using the CSE-CIC-IDS 2018 dataset.

**Figure 17.**Comparison between existing and proposed classification techniques based on the measures of accuracy, TPR, FPR, and F1-score.

**Figure 18.**Comparative analysis between existing and proposed techniques using the SCADA network dataset.

**Figure 19.**FAR of existing and proposed deep learning mechanisms for both the CSE-CIC-IDS 2018 and BoT-IoT datasets.

**Figure 20.**Detection rate of existing and proposed deep learning mechanisms for both the CSE-CIC-IDS 2018 and BoT-IoT datasets.

Attack Types | Size |
---|---|

Benign | 736,521 |

Bot | 143,010 |

DDoS-LOIC-UDP | 7085 |

DDoS-LOIC-HOIC | 1,082,293 |

DDoS-LOIC-HTTP | 296,084 |

DoS-GoldenEye | 30,585 |

DoS-Hulk | 90,051 |

DoS-Sloworis | 13,475 |

SSH-Bruteforce | 94,237 |

FTP-Bruteforce | 193,360 |

Infiltration | 209 |

Bruteforce-Web | 268 |

Bruteforce-XSS | 117 |

SQL-Injection | 53 |

Category | Type of Attack | Flow Count |
---|---|---|

Benign | Benign | 9543 |

Information gathering | Service scanning | 1,463,364 |

OS Fingerprinting | 358,275 | |

DDoS attack | DDoS TCP | 19,547,603 |

DDoS UDP | 18,965,106 | |

DDoS HTTP | 19,771 | |

DoS attack | DoS TCP | 12,315,997 |

DoS UDP | 20,659,491 | |

DoS HTTP | 29,706 | |

Information theft | Key logging | 1469 |

Data theft | 118 | |

Total | 73,370,443 |

**Table 3.**Comparative analysis between existing and proposed mechanisms using the CSE-CIC-IDS 2018 dataset.

Methods | Accuracy | TPR | FPR | F1-Score |
---|---|---|---|---|

Logistic Regression | 92.2 | 76.7 | 0.46 | 76.7 |

LDA | 88.2 | 64.8 | 0.70 | 64.8 |

Decision Tree | 99.4 | 98.2 | 0.03 | 98.2 |

NB | 91.7 | 75.1 | 0.49 | 75.1 |

SVM RBF | 84.1 | 52.3 | 0.95 | 52.3 |

SVM Linear | 80.2 | 40.6 | 1.18 | 40.6 |

Random Forest | 99 | 97 | 0.05 | 97 |

MLP | 90.9 | 72.8 | 0.54 | 72.8 |

Ada Boost | 84.6 | 53.8 | 0.92 | 53.8 |

Quadratic Discriminant Analysis | 72.2 | 1.66 | 1.66 | 1.66 |

Dense DNN | 98.4 | 95.4 | 0.09 | 95.4 |

Dense DNN Tanh | 96.5 | 89.7 | 0.20 | 89.7 |

Proposed GDSMO-DSLSTM | 99 | 99.3 | 0.18 | 98.5 |

Methods | Accuracy | TPR | FPR | F1-Score |
---|---|---|---|---|

ABOD | 94.4 | 100 | 10.1 | 94.2 |

Isolation Forest | 93.8 | 99.9 | 11.1 | 93.7 |

LOF | 94.4 | 100 | 1.01 | 94.2 |

Auto Encoder | 95.14 | 100 | 0.96 | 95.33 |

GDSMO-DSLSTM | 98.8 | 100 | 0.85 | 98 |

**Table 5.**Accuracy, detection rate, and F1-score of existing and proposed classification techniques using the SCADA network dataset.

Techniques | Accuracy | Detection Rate | F1-Score |
---|---|---|---|

Decision Forest | 99.72 | 94.12 | 80.26 |

Boosted Decision Forest | 99.77 | 93.14 | 84.67 |

Decision Jungle | 99.79 | 93.97 | 85.08 |

Cyber physical model | 99.79 | 99.78 | 98.7 |

Proposed GDSMO-DSLSTM | 99.8 | 99.85 | 99.8 |

**Table 6.**Comparative analysis between the existing and proposed deep learning techniques based on FAR.

Techniques | CSE-CIC-IDS 2018 | BoT-IoT |
---|---|---|

DNN | 1.3 | 1.45 |

RNN | 1.2 | 1.2 |

CNN | 1 | 1.1 |

RBM | 1.12 | 1.135 |

DBN | 1.11 | 1.12 |

DBM | 1.11 | 1.115 |

DA | 1.10 | 1.11 |

GDSMO-DSLSTM | 0.9 | 0.95 |

**Table 7.**Comparative analysis between the existing and proposed deep learning techniques based on detection rate.

Techniques | CSE-CIC-IDS 2018 | BoT-IoT |
---|---|---|

DNN | 95 | 97.5 |

RNN | 98 | 97.5 |

CNN | 98 | 97.5 |

RF | 92.5 | 92.5 |

NB | 82 | 80 |

SVM | 93 | 90 |

ANN | 90 | 89 |

GDSMO-DSLSTM | 98 | 97 |

Methods | Precision | Recall | F1-Measure |
---|---|---|---|

FNN | 88 | 89.2 | 87.4 |

LSTM | 99.54 | 99.01 | 99.27 |

Ensemble Learning | 99.76 | 99.57 | 99.68 |

GDSMO-DSLSTM | 99.8 | 99.8 | 99.85 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Khadidos, A.O.; Manoharan, H.; Selvarajan, S.; Khadidos, A.O.; Alyoubi, K.H.; Yafoz, A.
A Classy Multifacet Clustering and Fused Optimization Based Classification Methodologies for SCADA Security. *Energies* **2022**, *15*, 3624.
https://doi.org/10.3390/en15103624

**AMA Style**

Khadidos AO, Manoharan H, Selvarajan S, Khadidos AO, Alyoubi KH, Yafoz A.
A Classy Multifacet Clustering and Fused Optimization Based Classification Methodologies for SCADA Security. *Energies*. 2022; 15(10):3624.
https://doi.org/10.3390/en15103624

**Chicago/Turabian Style**

Khadidos, Alaa O., Hariprasath Manoharan, Shitharth Selvarajan, Adil O. Khadidos, Khaled H. Alyoubi, and Ayman Yafoz.
2022. "A Classy Multifacet Clustering and Fused Optimization Based Classification Methodologies for SCADA Security" *Energies* 15, no. 10: 3624.
https://doi.org/10.3390/en15103624