SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOT

Smart sentry CTI in IIOT

1. SMART SENTRY CYBER THREAT INTELLIGENCE IN IOT Name of the Guide: Mr S Girish Chandra Designation: Assistant Professor Members of batch: M Lakshmi Rama Chandra Mouli A Naga Tanmai R Sri Sowmya Shaik Majeed Mohammad Akbar

2. Table of Contents : Problem Statement Abstract Literature Survey Existing System Vs Proposed System Architecture Data Collection Algorithm – Results Output Screens Conclusion

3. PROBLEM STATEMENT: The increasing interconnectivity of Industrial Internet of Things ( IIoT ) systems has significantly enhanced operational efficiency but also introduced vulnerabilities to cyber threats that jeopardize critical infrastructure security. Traditional security measures are often inadequate in addressing the complexities and unique challenges posed by IIoT environments, where the scale of data and the speed of operations demand more advanced solutions.

4. ABSTRACT : Smart Sentry is an innovative Cyber Threat Intelligence (CTI) framework designed specifically for the Industrial Internet of Things ( IIoT ) environments, where the security of critical infrastructure is paramount. With the increasing integration of IoT devices in industrial settings, the potential for cyber threats has escalated, necessitating advanced solutions for detection and mitigation. This project leverages a combination of machine learning and deep learning techniques, including Random Forest, Decision Tree, Support Vector Machine, k-Nearest Neighbor, and Deep Neural Networks, to enhance threat detection capabilities. By employing real-time data analysis and proactive anomaly detection methods, Smart Sentry aims to ensure the operational integrity and resilience of IIoT infrastructures, ultimately safeguarding critical assets from emerging cyber threats.

5. LITERATURE SURVEY S.NO YEAR AUTHORS TITLE OUTCOMES 1 2022 E. Gyamfi and A. Jurcut Intrusion detection in Internet of Things systems: A review on design approaches leveraging multi-access edge computing, machine learning, and datasets A review of design approaches for intrusion detection in IoT systems, leveraging multi-access edge computing, machine learning, and datasets. 2 2022 E. Chatzoglou , G. Kambourakis , C. Smiliotopoulos , and C. Kolias Best of both worlds: Detecting application layer attacks through 802.11 and non-802.11 features A method for detecting application layer attacks using both 802.11 and non-802.11 features. 3 2023 C. Hazman , A. Guezzaz , S. Benkirane , and M. Azrour LIDS- SIoEL : Intrusion detection framework for IoT -based smart environments security using ensemble learning An intrusion detection framework (LIDS- SIoEL ) for IoT -based smart environments using ensemble learning.

6. 4 2023 V. Hnamte and J. Hussain DCNNBiLSTM : An efficient hybrid deep learning-based intrusion detection system A hybrid deep learning model ( DCNNBiLSTM ) for intrusion detection. 5 2023 W. Ding, M. Abdel-Basset, and R. Mohamed DeepAK-IoT : An effective deep learning model for cyberattack detection in IoT networks An effective deep learning model ( DeepAK-IoT ) for cyberattack detection in IoT networks. 6 2024 J. Liu, Y. Tang, H. Zhao, X. Wang, F. Li, and J. Zhang CPS attack detection under limited local information in cyber security: An ensemble multi-node multi-class classification approach An ensemble multi-node multi-class classification approach for CPS attack detection with limited local information.

7. EXISTING SYSTEM Vs PROPOSED SYSTEM Feature Existing System Proposed System Threat Detection Approach Traditional methods with some ML applications (e.g., k-NN for anomaly detection) Advanced ML and DL algorithms (Random Forest, Decision Trees, SVM, DNN) for real-time CTI False Positive Rates High false positive rates Aims to reduce false positive rates through advanced algorithms Anomaly Detection Uses k-NN for basic anomaly detection Uses a range of algorithms for comprehensive anomaly detection, including handling imbalanced data Proactive Security Some proactive elements through anomaly detection Strong focus on proactive security measures with continuous monitoring and threat intelligence Scalability Limited scalability, struggles with complex IIoT networks Highly scalable, adapts to evolving IIoT infrastructures

8. ARCHITECTURE

9. Dataset : -https://www.kaggle.com/datasets/sibasispradhan/edge-iiotset-dataset?select=live_data_training.csv The dataset from Kaggle . DATA COLLECTION

10. ALGORITHM - RESULTS DECISION TREE : Decision Tree is a Supervised learning technique   that can be used for both classification and Regression problems. It is a tree-structured classifier, where   internal nodes represent the features of a dataset, branches represent the decision rules and each leaf node represents the outcome.

11. RANDOM FOREST : Random Forest algorithm is a powerful tree learning technique in Machine Learning. It works by creating a number of Decision Trees during the training phase. Each tree is constructed using a random subset of the data set to measure a random subset of features in each partition.

12. EXTRA TREE CLASSIFIER : The Extra Trees Classifier (Extremely Randomized Trees) is an ensemble learning method used for classification tasks. It constructs a multitude of decision trees and merges their predictions to improve accuracy and control overfitting.

13. SUPPORT VECTOR MACHINE : SVM is a supervised machine learning algorithm primarily used for classification tasks but can also be applied to regression. It aims to find the optimal hyperplane that best separates data points of different classes in a high-dimensional space.

14. K-NEAREST NEIGHBORS : K -NN is a algorithm used for both classification and regression tasks in machine learning. It operates on the principle that similar data points are located close to each other in feature space.

15. DEEP NEURAL NETWORK : A Deep Neural Network (DNN) is a type of artificial neural network with multiple layers of nodes (neurons) between the input and output layers. It is designed to model complex relationships in data and is widely used in machine learning tasks.

16. Accuracy Comparison Plot Models Comparison for Classification

17. OUTPUT SCREENS Home Page:

18. About Page:

19. Registration Page:

20. Login Page :

21. Home Page :

22. Upload Page :

23. Model Selection Page :

24. Prediction Page:

25. CONCLUSION: In conclusion, Smart Sentry's Cyber Threat Intelligence framework significantly enhances the security of Industrial Internet of Things ( IIoT ) systems by integrating advanced machine learning and deep learning techniques. By employing algorithms such as Random Forest, Decision Tree, Extra Tree Classifier, Support Vector Machine, k-Nearest Neighbor, and Deep Neural Network, the framework effectively identifies and mitigates cyber threats in real-time. The implementation of techniques ensures that the models remain robust against data imbalances, which are prevalent in IIoT environments.

26. THANK YOU