Deep Learning for Intrusion Detection : Techniques and Applications

Click to enlarge

ISBN No.:	9781394285167
Pages:	336
Year:	202601
Format:	Trade Cloth (Hard Cover)
Price:	$ 193.20
Dispatch delay:	Dispatched between 7 to 15 days
Status:	Available (Forthcoming)

Qty: Add to Cart

Synopsis
Table of contents
Full Details

About the Editors xix List of Contributors xxi Foreword xxv Preface xxvii Acknowledgments xxix 1 Intrusion Detection in the Age of Deep Learning: An Introduction 1 Faheem Syeed Masoodi 1.1 Introduction 1 1.1.1 The Pioneers of Network Security 2 1.1.1.1 Limitations of the Existing System 2 1.1.

2 How Firewalls Are Different from IDS 3 1.1.3 Need for Intrusion Detection Systems 4 1.1.4 Intrusion Detection System 5 1.1.4.1 Intrusion Detection Technologies 9 1.

1.4.2 Intrusion Detection Methodologies 14 1.1.4.3 Intrusion Detection Approaches 17 1.1.5 Need for Deep Learning Based IDS 21 References 22 2 Machine Learning for Intrusion Detection 25 Divya M.

K. 2.1 Introduction 25 2.1.1 Overview of Intrusion Detection Systems (IDSs) 25 2.1.1.1 Types of IDSs: Host-Based, Network-Based, Hybrid 26 2.

2 Role of Machine Learning in IDSs 29 2.2.1 Benefits and Challenges of Using Machine Learning in IDSs 29 2.2.1.1 Benefits of ML in IDSs 29 2.2.1.

2 Challenges of ML in IDS 29 2.2.2 Evolution from Traditional Methods to ML-Based Approaches in IDSs 30 2.2.2.1 Traditional Methods in IDSs 30 2.2.2.

2 Transition to ML-Based Approaches 31 2.2.2.3 Current ML-Based IDS Landscape 31 2.3 Fundamentals of Machine Learning 32 2.3.1 Key ML Techniques 32 2.3.

1.1 How These Concepts Enable Pattern and Anomaly Detection 33 2.3.2 Key Algorithms Used in Intrusion Detection 33 2.3.3 Classification Algorithms 33 2.3.3.

1 Clustering Algorithms 34 2.3.3.2 Anomaly Detection Algorithms 35 2.4 Data Preparation for IDSs 35 2.4.1 Types of Data Used in IDSs 36 2.4.

2 Data Preprocessing Techniques 37 2.5 Supervised Learning for Intrusion Detection 37 2.5.1 Key Components of Supervised Learning 37 2.5.2 Benefits of Supervised Learning in IDSs 38 2.5.3 Challenges of Supervised Learning in IDSs 38 2.

5.4 Common Supervised Learning Techniques in IDSs 39 2.5.5 Supervised Learning Algorithms 39 2.5.6 Practical Example: Using Supervised Learning in IDSs 41 2.6 Unsupervised Learning for Intrusion Detection Systems (IDSs) 41 2.6.

1 Techniques and Algorithms 43 2.6.2 Example Use Case: Anomaly-Based Network Intrusion Detection 44 2.7 Semi-Supervised Learning in Intrusion Detection Systems (IDSs) 44 2.7.1 Semi-Supervised Algorithms and Applications 46 2.7.2 Applications in IDSs 48 2.

7.3 Example Use Case: Semi-Supervised Network Intrusion Detection 49 2.8 Reinforcement Learning for Intrusion Detection System 49 2.8.1 Example Scenario 51 2.9 Feature Engineering, Model Training, and Hyperparameter Tuning in Ids 53 2.9.1 Feature Engineering in IDS 53 2.

9.2 Model Training in IDS 54 2.9.3 Hyperparameter Tuning in IDSs 55 2.9.4 Practical Implementation Challenges in IDSs 56 References 56 3 Deep Learning Fundamentals-I 59 Razeef Mohd and Abeena Mohiudin Azad 3.1 Introduction to Deep Learning 59 3.1.

1 Definition and Importance 59 3.1.2 Deep Learning in Cybersecurity: Enhancing Threat Detection and Prevention 61 3.1.3 Key Areas Where Deep Learning Enhances Cybersecurity 61 3.1.3.1 Proactive Threat Detection with Deep Learning 62 3.

2 Conceptual Foundations of Deep Learning 63 3.2.1 Historical Evolution of Deep Learning 63 3.2.2 Key Differences Between Deep Learning and Traditional Machine Learning 64 3.2.3 Why Deep Learning Is Suited for Intrusion Detection 64 3.2.

4 Artificial Neural Networks (ANNs) as the Core of Deep Learning 65 3.2.4.1 Structure of ANNs 65 3.2.4.2 Working Mechanism of ANNs 65 3.2.

4.3 The Role of Deep Learning in Pattern Recognition and Anomaly Detection 66 3.3 Neural Networks: The Building Blocks of Deep Learning 66 3.3.1 Biological Inspiration and Mathematical Representation 66 3.3.2 Architecture of Neural Networks (Layers, Activation Functions, and Weights) 67 3.3.

2.1 Layers in Neural Networks 67 3.3.2.2 Neuron Activation Function 68 3.3.2.3 Types of Activation Functions 68 3.

3.3 Training Deep Learning Models Using Backpropagation and Weight Optimization 69 3.3.3.1 Error Functions in Neural Networks 70 3.3.3.2 Steps in Backpropagation 70 3.

3.4 Gradient Descent: The Backbone of Learning in Neural Networks 71 3.3.4.1 Advanced Optimization Techniques 72 3.3.5 Regularization Techniques in Neural Networks 73 3.3.

5.1 L1 and L2 Regularization 73 3.3.6 Dropout: Reducing Overfitting 73 3.3.6.1 Impact of Activation Functions and Optimization on Deep Learning 74 3.4 Applications of Deep Learning in Intrusion Detection 75 3.

4.1 Types of Cyber Threats and Attacks 75 3.4.1.1 DDoS Attacks 75 3.4.1.2 Malware and Ransomware 75 3.

4.1.3 Brute Force Attacks 75 3.4.1.4 Insider Threats 76 3.4.2 Deep Learning-Based Intrusion Detection Systems (IDSs) 76 3.

4.2.1 Signature-Based IDS 76 3.4.2.2 Anomaly-Based IDS 76 3.4.2.

3 Deep Learning Models Commonly Used for IDSs 77 3.4.3 Case Studies and Real-World Implementations 77 3.4.3.1 Financial Institutions 77 3.4.3.

2 Technology Companies 78 3.4.3.3 Healthcare Organizations 78 3.4.3.4 Government Agencies 78 3.4.

3.5 Retail and E-Commerce 78 3.5 Security-Enhancing Potential of Deep Learning 79 3.5.1 Advantages of Deep Learning in Cybersecurity 79 3.5.1.1 Automated Threat Detection 79 3.

5.1.2 High Accuracy 79 3.5.1.3 Scalability 80 3.5.1.

4 Adaptability to Evolving Threats 80 3.5.1.5 Reduced False Positives 80 3.5.2 Challenges and Limitations of Deep Learning-Based IDS 80 3.5.2.

1 Computational Costs 81 3.5.2.2 Adversarial Attacks 81 3.5.2.3 Data Availability and Quality 81 3.5.

3 Future Directions in AI-Driven Intrusion Detection 82 3.5.3.1 Federated Learning 82 3.5.3.2 Explainable AI (XAI) 82 3.5.

3.3 Integration with Blockchain 82 3.5.3.4 Continuous Learning and Adaptation 83 3.6 Conclusion 83 3.6.1 Summary of Key Insights 83 3.

6.2 Future Directions in Deep Learning for Cybersecurity 84 References 84 4 Deep Learning Fundamentals-II 91 Saduf Afzal, Shifaa Basharat, and Shozab Khurshid 4.1 Introduction 91 4.2 Artificial Neural Networks 92 4.3 Overview of Deep Learning 94 4.4 Deep Learning Algorithms 95 4.4.1 Deep Neural Networks (DNNs) 95 4.

4.2 Deep Belief Networks 96 4.4.3 Autoencoders 97 4.4.4 Convolutional Neural Network 98 4.4.5 Recurrent Neural Networks 99 4.

5 Conclusion 102 References 102 5 Intrusion Detection Through Deep Learning: Emerging Trends and Challenges 107 Achyutananda Mishra 5.1 Introduction 107 5.2 Deep Learning 108 5.2.1 Neural Network Architectures 109 5.2.2 Types of Neural Networks 110 5.2.

2.1 Feed-forward Neural Networks (FNNs) 110 5.2.2.2 Convolutional Neural Networks (CNNs) 111 5.2.2.3 Recurrent Neural Networks (RNNs) 111 5.

2.2.4 Recursive Neural Networks (RvNNs) 112 5.3 Applications of Deep Learning 112 5.4 Intrusion Detection 113 5.4.1 Classification 116 5.5 Methodologies of Detection 116 5.

6 Deep Learning for Intrusion Detection 117 5.7 Limitations 119 5.7.1 Mr. William''s Case 119 5.7.2 Challenges 120 5.8 Conclusion 120 References 121 6 Dataset for Evaluating Deep Learning-Based Intrusion Detection 125 Wasia Ashraf, Faheem Syeed Masoodi, and Asra Khanam 6.

1 Introduction 125 6.2 Data 126 6.2.1 Packet-Based Data 126 6.2.2 Flow-Based Data 127 6.2.3 Other Data 127 6.

3 Dataset Properties 128 6.3.1 Basic Information 128 6.3.2 Nature of Data 129 6.3.3 Data Volume 129 6.3.

4 Recording Environment 129 6.3.5 Evaluation 130 6.4 Datasets 131 6.4.1 Darpa 131 6.4.2 Kdd 1999 133 6.

4.3 Nsl-kdd 134 6.4.4 Iscx- 2012 137 6.4.5 Unsw-nb 15 139 6.4.6 Cic-ids- 2017 141 6.

5 Conclusion 143 References 144 7 Deep Learning Features: Techniques for Extraction and Selection 147 K.S. Shashikala, Sneha Shinde, Sandyarani Vadlamudi, and Mahendra Shridhar Naik 7.1 Introduction 147 7.1.1 Overview of Intrusion Detection Systems (IDSs) 147 7.1.2 Role of Deep Learning in IDSs 148 7.

1.3 Importance of Feature Extraction and Selection 149 7.1.3.1 Feature Extraction 149 7.1.3.2 Feature Selection 149 7.

1.3.3 Critical Role in IDSs 150 7.1.4 Improvement in Accuracy, Complexity Reduction, and Efficiency Enhancement 150 7.1.5 Challenges in Managing High-Dimensional Data in IDSs 152 7.2 Techniques for Feature Extraction and Selection 153 7.

2.1 Principal Component Analysis 153 7.2.2 Linear Discriminant Analysis 153 7.2.3 Mutual Information 154 7.2.3.

1 How Mutual Information Works? 154 7.2.4 Chi-Squared Feature Selection 155 7.2.4.1 How Chi-Squared Feature Selection Works? 155 7.2.5 Comparative Analysis of Techniques 156 7.

3 Applications in Intrusion Detection Systems 158 7.3.1 Integrating Feature Extraction and Selection in IDS Workflows 158 7.3.1.1 Impact on Performance 159 7.3.1.

2 Challenges in Real-World Applications 159 7.3.2 Performance Improvements 159

To be able to view the table of contents for this publication then please subscribe by clicking the button below...

To be able to view the full description for this publication then please subscribe by clicking the button below...