Intelligent Approach to Cyber Security provides details on the important cyber security threats and its mitigation and the influence of Machine Learning, Deep Learning and Blockchain technologies in the realm of cyber security.
As the internet is a very open and unprotected method of communication, it has attracted numerous miscreants with nefarious purposes. These criminals have made repeated attempts to get information and misuse it. Hence, the number of cyber-attacks and cybercrimes has increased exponentially with the growth of high-speed internet users. Cyber security is a significant issue in this setting that needs in-depth research and analysis.
The advent of technologies like Machine Learning, Deep Learning, Artificial Intelligence (AI) and blockchain have brought about a paradigm shift in the way security issues are handled. Incorporating these technologies in different aspects of cyber security has increased the robustness of various security mechanisms. Hence, the main aim of the book is to study the impact of these technologies on cyber security.
Authentication and access control are ways in which a layer of security can be implemented, and, hence, studying the same is important. The employment and the impact of state-of-the-art technologies like Machine Learning, Deep Learning, Artificial Intelligence and blockchain in different fields are also studied and covered.
The book is divided into a number of sections to arrange its contents effectively. The themes discussed vary from the requirements of technologies like Machine Learning, Deep Learning and blockchain in many areas to the usefulness of these technologies in cyber security. The book also offers new developments and research concerns relevant to the subject.
Eleven chapters make up the book, and address themes like comprehending the importance of Machine Learning and Deep Learning, as well as how these technologies – along with blockchain – can be critical to many aspects of cyber security.
Features:
Role of Deep Learning and Machine Learning in the Field of Cyber Security
Using ML to defend against cyber-attacks
Using DL to defend against cyber-attacks
Using blockchain to defend against cyber-attacks
This reference text will be useful for students and researchers interested and working in future cyber security issues in the light of emerging technology in the cyber world.
Author(s): Narendra M. Shekokar, Hari Vasudevan, Surya S. Durbha, Antonis Michalas
Publisher: CRC Press
Year: 2023
Language: English
Pages: 210
Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Section I: Introduction to Machine Learning in Cyber Security
Chapter 1: Introduction and Importance of Machine Learning Techniques in Cyber Security
1.1 Introduction
1.2 Importance of ML Techniques in Cyber Security
1.2.1 Common Vulnerabilities
1.2.2 Assets That Need to Be Protected
1.2.3 Role of Machine Learning in Cyber Security
1.3 Stages of a Cyber-Attack
1.4 Conclusion
References
Chapter 2: Review of Machine Learning Approaches in the Field of Healthcare
2.1 Introduction
2.2 Machine Learning Algorithms
2.3 Machine Learning Models
2.4 Disease Detection Using ML
2.4.1 Thyroid Disease
2.4.1.1 Methodology
2.4.2 Heart Disease
2.4.2.1 Methodology
2.4.3 Breast Cancer
2.4.3.1 Methodology
2.4.4 Diabetes
2.4.4.1 Methodology
2.4.5 Voice Disorder
2.4.5.1 Methodology
2.5 Security in Machine Learning/Deep Learning (ML/DL) for Healthcare
2.6 Security of ML
2.6.1 Security Threats
2.7 Conclusion and Future Scope
References
Chapter 3: Scope of Machine Learning and Blockchain in Cyber Security
3.1 Introduction
3.2 Machine Learning for Cyber Security
3.2.1 Threat Model for ML
3.3 Blockchain for Cyber Security
3.3.1 Threat Model for Blockchain
3.4 Proposed Approach
3.5 Conclusion and Future Work
References
Section II: Defending Against Cyber Attack Using Machine Learning
Chapter 4: Detection of Spear Phishing Using Natural Language Processing
4.1 Introduction
4.2 Literature Review
4.3 Dataset
4.4 Data Preprocessing
4.5 Textual Anomaly Detection System
4.5.1 Style Detection
4.5.1.1 Architecture of AWD-LSTM
4.5.1.2 Training of the Proposed Model
4.6 Experimentation and Results
4.7 Future Applications
4.8 Conclusion
References
Chapter 5: A Study of Recent Techniques to Detect Zero-Day Phishing Attacks
5.1 Introduction
5.2 Phishing Detection Approaches
5.2.1 Education-Based Detection
5.2.2 List-Based Detection
5.2.3 Heuristic-Based Detection
5.2.4 Content-Based Detection
5.2.5 Hybrid Detection Technique
5.3 Phishing Detection Using Machine Learning
5.4 Anti-Phishing Solutions Using Neural Networks/Deep Learning
5.4.1 Solutions Using Neural Networks
5.4.2 Solutions Using Deep Learning
5.5 Machine Learning as a Warhead
5.6 Comparative Analysis of the Techniques
5.7 Conclusion
References
Chapter 6: Analysis of Intelligent Techniques for Financial Fraud Detection
6.1 Introduction
6.2 Financial Fraud Detection Approaches
6.2.1 Machine Learning Approach for Financial Fraud Detection
6.2.1.1 Challenges in the Machine Learning Approach
6.2.1.2 Limitations of the Machine Learning Approach
6.2.2 Deep Learning Approach for Financial Fraud Detection
6.2.2.1 Challenges in the Deep Learning Approach
6.2.2.2 Limitations of the Deep Learning Approach
6.3 Literature Survey
6.3.1 Literature Survey for Machine Learning Approach
6.3.2 Literature Survey for Deep Learning Approach
6.4 Proposed Model Architecture
6.5 Confusion Matrix
6.6 Comparative Analysis of Decision Tree, SVM and Random Forest Algorithms
6.7 Conclusion
6.8 Future Scope
References
Further Reading
Chapter 7: Evaluation of Learning Techniques for Intrusion Detection Systems
7.1 Introduction
7.2 Review of Literature
7.3 Dataset
7.4 Analysis of Machine Learning Techniques
7.4.1 Input Data
7.4.2 Number of Classes
7.4.3 Number of Training Instances for Each Class
7.4.3.1 Oversampling
7.4.3.2 Undersampling
7.4.4 Number of Features
7.5 Conclusion
References
Section III: Defending Against Cyber Attack Using Deep Learning
Chapter 8: Deep Neural Networks for Cybersecurity
8.1 Introduction
8.2 Pitfalls in Traditional Cyber Security
8.2.1 Denial-of-Service (DoS) Attacks
8.2.2 Social Engineering
8.2.3 Phishing
8.2.4 Malware
8.2.5 Data Breach
8.3 Proposed Deep Learning Architectures and Methodologies
8.3.1 Convolutional Neural Networks
8.3.2 Recurrent Neural Networks
8.3.3 Generative Adversarial Networks
8.4 Deep Learning Applications in Cyber Security
8.4.1 Intrusion Detection Systems (IDS/IPS) with Network Traffic Analytics
8.4.2 Social Engineering Detection
8.4.3 Malware Detection
8.5 Drawbacks and Future Scope
8.6 Conclusion
References
Chapter 9: Deep Learning in Malware Identification and Classification
9.1 Introduction
9.2 Malware and Its Variants
9.3 Current Malware Statistics
9.4 Malware Detection
9.4.1 Anomaly-Based Detection
9.4.2 Signature-Based Detection
9.5 Machine Learning in Malware Detection
9.5.1 Neural Networks for Malware Detection
9.5.1.1 Connections and Weights
9.5.1.2 Propagation Function/Activation Function
9.5.1.3 Learning Process
9.5.2 Detection Using Combined Features
9.6 Malware Visualization and Classification Using Deep Learning
9.6.1 Collection of Malware Samples and Preprocessing
9.6.2 Visualization of Malware as an Image
9.6.3 Training a Neural Network Model for Classification
9.6.4 Testing/Validation of a Model
9.7 Summary
References
Section IV: Defending Against Cyber Attack Using Advance Technology
Chapter 10: Cyber Threat Mitigation Using Machine Learning, Deep Learning, Artificial Intelligence, and Blockchain
10.1 Introduction
10.2 Literature Survey
10.3 Cyber Threats
10.3.1 What Is a Cyber Threat?
10.3.2 Cyber-Threat Actors
10.3.3 Sources of Cyber Threat
10.3.3.1 Terrorists
10.3.3.2 Insiders
10.3.3.3 Nations
10.3.4 Cyber-Threat Environment
10.3.5 Types of Cyber Threats
10.3.5.1 Botnets
10.3.5.2 Denial of Service
10.3.5.3 Man-in-the-Middle
10.3.5.4 Password Cracking
10.3.5.5 Ransomware
10.4 Using Technologies to Mitigate Cyber Threats
10.4.1 Comparison of Common Techniques
10.4.2 Artificial Intelligence
10.4.2.1 Introduction to AI in Cyber Security
10.4.2.2 Use of AI in Cyber Security
10.4.2.2.1 Exposing Cyber Threats
10.4.2.2.2 Prediction of Breaching
10.4.2.2.3 Response to Incidences
10.4.3 Machine Learning
10.4.3.1 Use of Machine Learning in Reducing Cyber Threats
10.4.3.1.1 Automated Security
10.4.3.1.2 Advanced Antivirus Programs
10.4.3.1.3 Bane or Boon?
10.4.4 Deep Learning
10.4.4.1 Deep learning for Detection
10.4.4.1.1 Email Surveillance
10.4.4.1.2 Network Traffic Monitoring
10.4.5 Blockchain
10.4.5.1 What Is Blockchain?
10.4.5.2 Nature of Blockchain
10.4.5.3 Use of Blockchain in Data Integrity
10.4.5.4 Use Cases of Blockchain in Cyber Security
10.4.5.4.1 Decentralized Storage
10.4.5.4.2 Securing DNS
10.5 Cyberinfrastructure
10.6 Conclusion
10.7 Future Scope
References
Chapter 11: Quantum-Safe Cryptography
11.1 Introduction
11.2 Current State of Cryptosystems
11.2.1 Security Issues with Current Cryptosystems
11.3 Current State of Post-Quantum Cryptography (PQC)
11.4 Challenges in Post-Quantum Cryptography (PQC)
11.5 Approaches for Post-Quantum Cryptography (PQC) Migration
11.5.1 Hybrid Scheme
11.5.2 Protective Measures for Pre-Quantum Cryptography
References
Index
