Intrusion Detection System Using Machine Learning Techniques

General Information:

Cover Page:

Outline:

Acronyms
General introduction
Chapter 1 Network Security
1.1 Definition
1.2 Key principles of network security
1.3 Different types of network security
1.3.1 Network Access Control (NAC)
1.3.2 Network segmentation
1.3.3 Behavioral analytics
1.3.4 Firewalls
1.3.5 Antivirus and Antimalware software
1.4 Anomaly detection and attack types
1.4.1 Anomaly types
1.4.2 Network attack types
1.5 Most common attacks
1.5.1 DOS HULK
1.5.2 DOS Slowloris
1.5.3 Botnet
1.5.4 Malware
1.5.5 Port scanning
1.5.6 FTP-Patator
1.5.7 SSH-Patator
1.5.8 Web attacks
1.5.9 IP spoofing
1.6 Conclusion
Chapter 2 Intrusion Detection System
2.1 Introduction
2.2 Definition
2.3 Components of intrusion detection systems
Data collection
2.3.1 Data pre-processor
2.3.2 Intrusion recognition
2.4 IDS functions
2.5 IDS Classification
2.5.1 Types of IDS
2.5.2 Detection methods
2.5.3 Location of data analysis
2.5.4 Behavior in case of detection of an attack
2.6 Conclusion
Chapter 3 Machine Learning & Deep Learning
3.1 Introduction
3.2 Brief overview of Machine Learning
3.3 Review of Artificial Neural Networks
3.3.1 History of Artificial Neural Networks
3.3.2 Modeling an artificial neuron
3.3.3 The Perceptron
3.3.4 Common activation functions
3.3.5 Loss function
3.3.6 Gradient descent algorithm
3.3.7 The Multi-Layer Perceptron
3.4 Convolution Neural Networks
3.5 Recurrent Neural Networks
3.6 Long Short Term Memory
3.7 AutoEncoders
3.8 Metrics for evaluating the model’s performance
3.8.1 Confusion matrix
3.8.2 Accuracy
3.8.3 Precision
3.8.4 Recall or Sensitivity or TPR
3.8.5 Specificity or TNR
3.8.6 FPR
3.8.7 FNR
3.8.8 F1 score
3.8.9 ROC curve
3.9 Conclusion
Chapter 4 Network anomaly detection, tests and results
4.1 Introduction
4.2 Execution environment
4.3 Dataset
4.3.1 Descriptions of CIC-IDS2017 dataset
4.4 Implementation
4.5 Data pre-processing
4.5.1 Data cleaning
4.5.2 Creation of Training and Test Data
4.5.3 Feature selection
4.6 Implementation of Machine Learning Algorithms
Decision Trees
4.6.1 Random Forest
4.6.2 K-Nearest Neighbors
4.6.3 Support Vector Machine
4.6.4 Multi Layer Perceptron
4.7 Results and Discussion
4.7.1 First approach – Using 7 attack types
4.7.2 Approach 2 – Using Two Groups: Normal and Abnormal
4.8 Comparative Study
4.9 Evaluation
4.10 Conclusion
General conclusion
Bibliography

Download The Thesis:

📥 تحميل الملف

For more
academic sources and references,
including theses and dissertations from Algerian universities,
, visit our main website.