Artificial Intelligence and Cyber Security in Industry 4.0

Preface
Contents
1 Introduction to Artificial Intelligence and Cybersecurity for Industry
	Introduction
		Classification of Cyberattacks (See Fig. 1.1)
		Types of Cybersecurity
	Tools Used in Cybersecurity
		Firewall
		Honeypots
		How Does Artificial Intelligence Work? (See Fig. 1.3)
	AI Implementation Methods
		Machine Learning
		Deep Learning
	Background Information on AI Methods and Cybersecurity Applications
	The Significance of Cybersecurity
		How AI Can Be Applied on Cybersecurity Issues
		AI Techniques Used for Cybersecurity
		Security Expert Systems
	Deep Learning Detection for Misinformation
	Benefits of AI in Cybersecurity
		Detecting False Information Using Neural Networks
		Using Neural Networks to Find Objectionable YouTube Content
	Challenges Faced with Integration of AI in Cybersecurity
		Classification Error
		Intensive Requirement for Resources
		Public Perception
	Discussion
	Conclusion
	References
2 Role of AI and Its Impact on the Development of Cyber Security Applications
	Introduction
		Overview of Artificial Intelligence
	Literature Survey
	Artificial Intelligence Techniques for Cyber Security
		Various Artificial Intelligence Tools and Techniques Are Mentioned Below
		Machine Learning Algorithm Used to Train a Machine
		Why AI is Preferred Over Current Anomaly Detection and Prevention Systems?
		Use Cases of Artificial Intelligence in Cyber Security
	Applications of AI in Cyber Security
		AI Solutions for Cyber Security [26]
	Limitations of AI in Security
		Ethical Issues Related to AI [27]
		AI-Based Threat to Cyber Security [27]
	Conclusion
	References
3 AI and IoT in Manufacturing and Related Security Perspectives for Industry 4.0
	Introduction
	Role of AI in Manufacturing
		Related Works
		Technologies
		Impact of AI in Manufacturing
		Uses Cases of AI in Manufacturing
	IoT in Manufacturing
		Related Works
		Technologies
		Need of IIoT Security
		Applications
	Vulnerabilities and Challenges
		Quality Control
		Threat Recognition
		Configuration of the Hardware
		Encryption of Data
		Confidentiality of Data
		Integration of Cyber-Physical Systems
		Devices Pairing Key Establishment
		Device Management
	Conclusion and Future Work
	References
4 IoT Security Vulnerabilities and Defensive Measures in Industry 4.0
	Introduction
	IoT/IIoT Security Challenges and Requirements
		IoT/IIoT Security Challenges
		Requirements for IoT/IIoT Security
	IoT Architecture and Security Attacks
		Architecture of IoT
		IoT Security Attacks in Architectural Perspective
	Preventive Techniques and Mechanisms of IoT/IIoT Security
		Preventive Techniques of IoT Security Attacks
		Mechanisms for Combating IoT/IIoT Security Attacks
	Conclusion
	References
5 Adopting Artificial Intelligence in ITIL for Information Security Management—Way Forward in Industry 4.0
	Introduction
		Definition of AI
		Definition of AI
	Application of AI in IT Service Management
		Artificial Intelligence for IT Operations
		Artificial Intelligence for IT Operations
	The Security Technology-Artificial Intelligence Cycle
		Operations Understanding Current Use of Artificial Intelligence in Security Technologies
	Artificial Intelligence and Its Application to Information Security Management
		AI Basics and Early Adopters
		Methods AI is Used in Information Security Management
	Artificial Intelligence (AI) Security Threats
		AI Basics and Early Adopters
		Physical Security
	Benefits/Areas of AI Applications in Information Security Management
		Threat Exposure
		Effectiveness Control
		Prediction of Breach Risks
		Response to Incidences
		Explainability
		Analysis
	Conclusions
	References
6 Intelligent Autonomous Drones in Industry 4.0
	Introduction
		Scope of Study
	Design of Drones
		Sensor Technologies
		Drone Platform
		Flight Concept
	Reactive Control of Autonomous Drones
		Legal Uncertainties
	Drone Obstacle Avoidance
		Parallelization of Local Path Planning for High-Reliable Autonomous Drones
		Short-Range Telemetry Communication for Autonomous Drone Navigation
		Autonomous Drone Guidance and Landing System Using AR Markers
		Detecting Rogue Drones
	Drones Application
		Drones in Manufacturing
		Autonomous Aerial Counter-Drone System
		Internet of Things
		Unmanned Aerial Vehicles (UAV) and Its Applications
		AI-Based Pipeline Inspection by Drone for Oil and Gas Industry in Bahrain
		Disaster Management
		Agricultural Drones
		Crowd Density Estimation Challenges and Solution
		Campus Priority System
		Autonomous Drone Control Within a Wi-Fi Network
		Improving Image Recognition Accuracy by Contrast Correction in Autonomous Drone Flight
	Susceptible Attack Methods Against Autonomous Drones
	Conclusion
	References
7 A Review on Automatic Generation of Attack Trees and Its Application to Automotive Cybersecurity
	Introduction
	Automotive Cybersecurity Assurance
	Attack Trees
	Literature Review Methodology
	Review of Attack Tree Generation Methods
	Attack Tree Generation in the Automotive Domain
	Challenges and New Directions in Attack Tree Generation for the Automotive Domain
		Trends in Research
		New Directions
	Conclusion and Future Research
	References
8 Malware Analysis Using Machine Learning Tools and Techniques in IT Industry
	Introduction
	Malware Analysis Using Machine Learning Techniques
		Algorithms for Malware Analysis
		Objectives of Malware Analysis
		Features in Malware Analysis
	Challenges of Malware Analysis
		Analysis-Resistant Malware
		Accuracy
	Case Study
	Conclusion
	References
9 Use of Machine Learning in Forensics and Computer Security
	Introduction
	History of Machine Learning
		Motivation
	The Methods in Machine Learning
		Supervised Machine Learning Algorithms
		Unsupervised Machine Learning Algorithms
		Reinforcement Machine Learning Algorithms
	Cyber Threat Intelligence
		What Does Threat Intelligence Do?
		Who Is a Cyber Threat Intelligence Analyst?
		What Does Threat Intelligence Do?
		Who Is a Cyber Threat Intelligence Analyst?
	Cyber Security
		The Domains of Cyber Security and Its Role in Society
		Principles of Cyber Security
		The Role of ML in Cybersecurity
	Importance of Threat Intelligence in Cybersecurity
		Security Team Efficiency
		Collaborative Knowledge
	Top Machine Learning Use Cases for Security
		Using Machine Learning to Detect Malicious Activity and Stop Attacks
		Using Machine Learning to Analyze Mobile Endpoints
		Using Machine Learning to Enhance Human Analysis
		Using Machine Learning to Automate Repetitive Security Tasks
		Using Machine Learning to Close Zero-Day Vulnerabilities
		Hype and Misunderstanding Muddy the Landscape
	Applications of Machine Learning in Cybersecurity
		Spear Phishing
		Watering Hole
		Webshell
		Ransomware
		Remote Exploitation
	How Does Machine Learning Benefit Cybersecurity?
	Conclusion
	Future Scope
	References
10 Control of Feed Drives in CNC Machine Tools Using Artificial Immune Adaptive Strategy
	Introduction
	CNC Machine
	Principles of CNC
	Principle and Operation of Brushless DC Motor
	Mathematical Model of BLDC Motor
	Commutation Torque Ripple
	Control of Feed Drives
	Artificial Immune System
	Simulation Study
	Comparative Study
	Conclusion
	References
11 Efficient Anomaly Detection for Empowering Cyber Security by Using Adaptive Deep Learning Model
	Introduction
	Related Works
	Proposed Methodology
		Datasets
		Data Pre-processing
		Classification
	Results and Discussion
	Conclusion
	References
12 Intrusion Detection in IoT-Based Healthcare Using ML and DL Approaches: A Case Study
	Introduction
	Attacks on IoT-Based Healthcare Ecosystem
		Physical Layer
		Software/Application Layer
		Network Layer
	Intrusion Detection in IoT-Based Healthcare
		Signature-Based Intrusion Detection System (SIDS)
	Anomaly-Based Intrusion Detection System (AIDS)
		Classification of AIDS
	Ensemble Classifier
	AIDS Deployment Techniques in IoT
		Centralized Intrusion Detection System
		Distributed Intrusion Detection System
		Hierarchical Intrusion Detection System
	AIDS Validation Techniques
		True Positive Rate (TPR)
		False Positive Rate (FPR)
		False Negative Rate (FNR)
		True Negative Rate (TNR)
		Accuracy
		Confusion Matrix
	Conclusion
	References
13 War Strategy Algorithm-Based GAN Model for Detecting the Malware Attacks in Modern Digital Age
	Introduction
	Related Works
	Proposed System
		Dataset Description
		Detection of Malware Using PATE-GAN
		Mathematical Model of the War Approach
	Results and Discussion
	Conclusion
	References
14 ML Algorithms for Providing Financial Security in Banking Sectors with the Prediction of Loan Risks
	Introduction
	Related Work
	Methodology
		Data Pre-processing
	Methodology
	Conclusion
	References
15 Machine Learning-Based DDoS Attack Detection Using Support Vector Machine
	Introduction
	Previous Work
	Distributed Denial of Service Attack
		Application Layer Attack
		Protocol Attack
		Syn Flood
		Volumetric Attacks
	SVM
		Hyperplane
		Support Vectors
		Linear SVM
		Nonlinear SVM
	Deduction of DDoS Through SVM: (SVMBD)
		SVM-Based Model Creation
		Training the Model
		Testing the Model
		Assessing the Quality of the Model Using Metrics
	Conclusion
	References
16 Artificial Intelligence-Based Cyber Security Applications
	Introduction
		Scope of Study
	Understanding Artificial Intelligence
		Basic Components of AI
		AI for Cyber Security
		Traditional System and AI Systems in Cyber Security
		AI’s Prevalence and Use in Cyber Security
		History of AI in Cyber Security Applications
	Gathering of Cyber Security Data for Training Models
	Artificial Intelligence for Cyber Security
		Expert Systems for Cyber Security
		Intelligent Agents
	Machine Learning for Cyber Security
		Understanding Machine Learning
		Machine Learning Algorithms
		Machine Learning Methods
		Machine Learning Methods for Cyber Threat Prevention
		Machine Learning Technology in Cyber Security
	Deep Learning for Cyber Security
		Choice of Deep Learning Over Machine Learning for Cyber Crime Detection
		Deep Learning Methods for Cyber Security
		Deep Learning Methods in Cyber Security Applications
	AI-Powered Cyber Security Platforms for Enterprises
	Performance of an AI Solution
		Performance Analysis Metrics of Artificial Intelligence Solutions
		Techniques to Enhance the Performance of Artificial Intelligence Solutions
	Downsides of Artificial Intelligence in Cyber Security
	Credit Card Fraud Detection System
	Conclusion and Future Work
	References