| Autore |
Masoodi Faheem Syeed
|
| Edizione | [1st ed.] |
| Pubbl/distr/stampa |
Newark : , : John Wiley & Sons, Incorporated, , 2026
|
| Descrizione fisica |
1 online resource (333 pages)
|
| Disciplina |
005.8/4
|
| Soggetto topico |
Intrusion detection systems (Computer security)
|
| ISBN |
1-394-28517-5
1-394-28519-1
1-394-28518-3
|
| Formato |
Materiale a stampa  |
| Livello bibliografico |
Monografia |
| Lingua di pubblicazione |
eng
|
| Nota di contenuto |
Cover -- Title Page -- Copyright -- Contents -- About the Editors -- List of Contributors -- Foreword -- Preface -- Acknowledgments -- Chapter 1 Intrusion Detection in the Age of Deep Learning: An Introduction -- 1.1 Introduction -- 1.1.1 The Pioneers of Network Security -- 1.1.1.1 Limitations of the Existing System -- 1.1.2 How Firewalls Are Different from IDS -- 1.1.3 Need for Intrusion Detection Systems -- 1.1.4 Intrusion Detection System -- 1.1.4.1 Intrusion Detection Technologies -- 1.1.4.2 Intrusion Detection Methodologies -- 1.1.4.3 Intrusion Detection Approaches -- 1.1.5 Need for Deep Learning Based IDS -- References -- Chapter 2 Machine Learning for Intrusion Detection -- 2.1 Introduction -- 2.1.1 Overview of Intrusion Detection Systems (IDSs) -- 2.1.1.1 Types of IDSs: Host‐Based, Network‐Based, Hybrid -- 2.2 Role of Machine Learning in IDSs -- 2.2.1 Benefits and Challenges of Using Machine Learning in IDSs -- 2.2.1.1 Benefits of ML in IDSs -- 2.2.1.2 Challenges of ML in IDS -- 2.2.2 Evolution from Traditional Methods to ML‐Based Approaches in IDSs -- 2.2.2.1 Traditional Methods in IDSs -- 2.2.2.2 Transition to ML‐Based Approaches -- 2.2.2.3 Current ML‐Based IDS Landscape -- 2.3 Fundamentals of Machine Learning -- 2.3.1 Key ML Techniques -- 2.3.1.1 How These Concepts Enable Pattern and Anomaly Detection -- 2.3.2 Key Algorithms Used in Intrusion Detection -- 2.3.3 Classification Algorithms -- 2.3.3.1 Clustering Algorithms -- 2.3.3.2 Anomaly Detection Algorithms -- 2.4 Data Preparation for IDSs -- 2.4.1 Types of Data Used in IDSs -- 2.4.2 Data Preprocessing Techniques -- 2.5 Supervised Learning for Intrusion Detection -- 2.5.1 Key Components of Supervised Learning -- 2.5.2 Benefits of Supervised Learning in IDSs -- 2.5.3 Challenges of Supervised Learning in IDSs -- 2.5.4 Common Supervised Learning Techniques in IDSs.
2.5.5 Supervised Learning Algorithms -- 2.5.6 Practical Example: Using Supervised Learning in IDSs -- 2.6 Unsupervised Learning for Intrusion Detection Systems (IDSs) -- 2.6.1 Techniques and Algorithms -- 2.6.2 Example Use Case: Anomaly‐Based Network Intrusion Detection -- 2.7 Semi‐Supervised Learning in Intrusion Detection Systems (IDSs) -- 2.7.1 Semi‐Supervised Algorithms and Applications -- 2.7.2 Applications in IDSs -- 2.7.3 Example Use Case: Semi‐Supervised Network Intrusion Detection -- 2.8 Reinforcement Learning for Intrusion Detection System -- 2.8.1 Example Scenario -- 2.9 Feature Engineering, Model Training, and Hyperparameter Tuning in IDS -- 2.9.1 Feature Engineering in IDS -- 2.9.2 Model Training in IDS -- 2.9.3 Hyperparameter Tuning in IDSs -- 2.9.4 Practical Implementation Challenges in IDSs -- References -- Chapter 3 Deep Learning Fundamentals‐I -- 3.1 Introduction to Deep Learning -- 3.1.1 Definition and Importance -- 3.1.2 Deep Learning in Cybersecurity: Enhancing Threat Detection and Prevention -- 3.1.3 Key Areas Where Deep Learning Enhances Cybersecurity -- 3.1.3.1 Proactive Threat Detection with Deep Learning -- 3.2 Conceptual Foundations of Deep Learning -- 3.2.1 Historical Evolution of Deep Learning -- 3.2.2 Key Differences Between Deep Learning and Traditional Machine Learning -- 3.2.3 Why Deep Learning Is Suited for Intrusion Detection -- 3.2.4 Artificial Neural Networks (ANNs) as the Core of Deep Learning -- 3.2.4.1 Structure of ANNs -- 3.2.4.2 Working Mechanism of ANNs -- 3.2.4.3 The Role of Deep Learning in Pattern Recognition and Anomaly Detection -- 3.3 Neural Networks: The Building Blocks of Deep Learning -- 3.3.1 Biological Inspiration and Mathematical Representation -- 3.3.2 Architecture of Neural Networks (Layers, Activation Functions, and Weights) -- 3.3.2.1 Layers in Neural Networks.
3.3.2.2 Neuron Activation Function -- 3.3.2.3 Types of Activation Functions -- 3.3.3 Training Deep Learning Models Using Backpropagation and Weight Optimization -- 3.3.3.1 Error Functions in Neural Networks -- 3.3.3.2 Steps in Backpropagation -- 3.3.4 Gradient Descent: The Backbone of Learning in Neural Networks -- 3.3.4.1 Advanced Optimization Techniques -- 3.3.5 Regularization Techniques in Neural Networks -- 3.3.5.1 L1 and L2 Regularization -- 3.3.6 Dropout: Reducing Overfitting -- 3.3.6.1 Impact of Activation Functions and Optimization on Deep Learning -- 3.4 Applications of Deep Learning in Intrusion Detection -- 3.4.1 Types of Cyber Threats and Attacks -- 3.4.1.1 DDoS Attacks -- 3.4.1.2 Malware and Ransomware -- 3.4.1.3 Brute Force Attacks -- 3.4.1.4 Insider Threats -- 3.4.2 Deep Learning‐Based Intrusion Detection Systems (IDSs) -- 3.4.2.1 Signature‐Based IDS -- 3.4.2.2 Anomaly‐Based IDS -- 3.4.2.3 Deep Learning Models Commonly Used for IDSs -- 3.4.3 Case Studies and Real‐World Implementations -- 3.4.3.1 Financial Institutions -- 3.4.3.2 Technology Companies -- 3.4.3.3 Healthcare Organizations -- 3.4.3.4 Government Agencies -- 3.4.3.5 Retail and E‐Commerce -- 3.5 Security‐Enhancing Potential of Deep Learning -- 3.5.1 Advantages of Deep Learning in Cybersecurity -- 3.5.1.1 Automated Threat Detection -- 3.5.1.2 High Accuracy -- 3.5.1.3 Scalability -- 3.5.1.4 Adaptability to Evolving Threats -- 3.5.1.5 Reduced False Positives -- 3.5.2 Challenges and Limitations of Deep Learning‐Based IDS -- 3.5.2.1 Computational Costs -- 3.5.2.2 Adversarial Attacks -- 3.5.2.3 Data Availability and Quality -- 3.5.3 Future Directions in AI‐Driven Intrusion Detection -- 3.5.3.1 Federated Learning -- 3.5.3.2 Explainable AI (XAI) -- 3.5.3.3 Integration with Blockchain -- 3.5.3.4 Continuous Learning and Adaptation -- 3.6 Conclusion -- 3.6.1 Summary of Key Insights.
3.6.2 Future Directions in Deep Learning for Cybersecurity -- References -- Chapter 4 Deep Learning Fundamentals‐II -- 4.1 Introduction -- 4.2 Artificial Neural Networks -- 4.3 Overview of Deep Learning -- 4.4 Deep Learning Algorithms -- 4.4.1 Deep Neural Networks (DNNs) -- 4.4.2 Deep Belief Networks -- 4.4.3 Autoencoders -- 4.4.4 Convolutional Neural Network -- 4.4.5 Recurrent Neural Networks -- 4.5 Conclusion -- References -- Chapter 5 Intrusion Detection Through Deep Learning: Emerging Trends and Challenges -- 5.1 Introduction -- 5.2 Deep Learning -- 5.2.1 Neural Network Architectures -- 5.2.2 Types of Neural Networks -- 5.2.2.1 Feed‐forward Neural Networks (FNNs) -- 5.2.2.2 Convolutional Neural Networks (CNNs) -- 5.2.2.3 Recurrent Neural Networks (RNNs) -- 5.2.2.4 Recursive Neural Networks (RvNNs) -- 5.3 Applications of Deep Learning -- 5.4 Intrusion Detection -- 5.4.1 Classification -- 5.5 Methodologies of Detection -- 5.6 Deep Learning for Intrusion Detection -- 5.7 Limitations -- 5.7.1 Mr. William's Case -- 5.7.2 Challenges -- 5.8 Conclusion -- References -- Chapter 6 Dataset for Evaluating Deep Learning‐Based Intrusion Detection -- 6.1 Introduction -- 6.2 Data -- 6.2.1 Packet‐Based Data -- 6.2.2 Flow‐Based Data -- 6.2.3 Other Data -- 6.3 Dataset Properties -- 6.3.1 Basic Information -- 6.3.2 Nature of Data -- 6.3.3 Data Volume -- 6.3.4 Recording Environment -- 6.3.5 Evaluation -- 6.4 Datasets -- 6.4.1 DARPA -- 6.4.2 KDD 1999 -- 6.4.3 NSL‐KDD -- 6.4.4 ISCX‐2012 -- 6.4.5 UNSW‐NB15 -- 6.4.6 CIC‐IDS‐2017 -- 6.5 Conclusion -- References -- Chapter 7 Deep Learning Features: Techniques for Extraction and Selection -- 7.1 Introduction -- 7.1.1 Overview of Intrusion Detection Systems (IDSs) -- 7.1.2 Role of Deep Learning in IDSs -- 7.1.3 Importance of Feature Extraction and Selection -- 7.1.3.1 Feature Extraction -- 7.1.3.2 Feature Selection.
7.1.3.3 Critical Role in IDSs -- 7.1.4 Improvement in Accuracy, Complexity Reduction, and Efficiency Enhancement -- 7.1.5 Challenges in Managing High‐Dimensional Data in IDSs -- 7.2 Techniques for Feature Extraction and Selection -- 7.2.1 Principal Component Analysis -- 7.2.2 Linear Discriminant Analysis -- 7.2.3 Mutual Information -- 7.2.3.1 How Mutual Information Works? -- 7.2.4 Chi‐Squared Feature Selection -- 7.2.4.1 How Chi‐Squared Feature Selection Works? -- 7.2.5 Comparative Analysis of Techniques -- 7.3 Applications in Intrusion Detection Systems -- 7.3.1 Integrating Feature Extraction and Selection in IDS Workflows -- 7.3.1.1 Impact on Performance -- 7.3.1.2 Challenges in Real‐World Applications -- 7.3.2 Performance Improvements -- 7.3.2.1 Efficiency Gains Through MI and Chi‐Squared Methods -- 7.3.2.2 Enhancing Scalability for Growing Network Demands -- 7.3.3 Practical Deployment -- 7.3.3.1 Preprocessing with PCA and LDA -- 7.3.3.2 Training with MI and Chi‐Squared Methods -- 7.3.3.3 Hybrid Approaches for Enhanced Results -- 7.3.3.4 Real‐World Applications -- 7.4 Conclusion and Future Trends -- 7.4.1 Key Insights -- 7.4.2 Future Directions -- References -- Chapter 8 Exploring Advanced Artificial Intelligence for Anomaly Detection -- 8.1 Introduction -- 8.1.1 Types of Anomalous Detection -- 8.1.2 Artificial Intelligence‐Based Anomaly Detection -- 8.1.2.1 AI‐Based AD Process -- 8.1.2.2 Machine Learning Algorithms for AD -- 8.1.2.3 Application Domains -- 8.1.2.4 Advantages of AI‐Based AD Methods -- 8.1.2.5 Challenges in AI‐Based AD -- 8.1.2.6 AI‐Based AD Methods -- 8.2 Autoencoder‐Based Anomaly Detection -- 8.2.1 Types of Autoencoders -- 8.3 Generative Adversarial Networks Anomaly Detection -- 8.3.1 Features of GANs -- 8.3.2 Working Principle of GANs -- 8.4 One‐Class Classification Anomaly Detection.
8.5 Deep Reinforcement Learning Anomaly Detection.
|
| Record Nr. | UNINA-9911042411803321 |
Info
24th International Symposium on Research in Attacks, Intrusions and Defenses / / Association for Computing Machinery
