Artificial Intelligence and Data Mining Approaches in Security Frameworks

ARTIFICIAL INTELLIGENCE AND DATA MINING IN SECURITY FRAMEWORKS Written and edited by a team of experts in the field, this outstanding new volume offers solutions to the problems of security, outlining the concepts behind allowing computers to learn from experience and understand the world in terms of a hierarchy of concepts, with each concept de?ned through its relation to simpler concepts. Artificial intelligence (AI) and data mining is the fastest growing field in computer science. AI and data mining algorithms and techniques are found to be useful in different areas like pattern recognition, automatic threat detection, automatic problem solving, visual recognition, fraud detection, detecting developmental delay in children, and many other applications. However, applying AI and data mining techniques or algorithms successfully in these areas needs a concerted effort, fostering integrative research between experts ranging from diverse disciplines from data science to artificial intelligence. Successful application of security frameworks to enable meaningful, cost effective, personalized security service is a primary aim of engineers and researchers today. However realizing this goal requires effective understanding, application and amalgamation of AI and data mining and several other computing technologies to deploy such a system in an effective manner. This book provides state of the art approaches of artificial intelligence and data mining in these areas. It includes areas of detection, prediction, as well as future framework identification, development, building service systems and analytical aspects. In all these topics, applications of AI and data mining, such as artificial neural networks, fuzzy logic, genetic algorithm and hybrid mechanisms, are explained and explored. This book is aimed at the modeling and performance prediction of efficient security framework systems, bringing to light a new dimension in the theory and practice. This groundbreaking new volume presents these topics and trends, bridging the research gap on AI and data mining to enable wide-scale implementation. Whether for the veteran engineer or the student, this is a must-have for any library. This groundbreaking new volume: Clarifies the understanding of certain key mechanisms of technology helpful in the use of artificial intelligence and data mining in security frameworks Covers practical approaches to the problems engineers face in working in this field, focusing on the applications used every day Contains numerous examples, offering critical solutions to engineers and scientists Presents these new applications of AI and data mining that are of prime importance to human civilization as a whole

Table of Contents:
Preface xiii 1 Role of AI in Cyber Security 1 Navani Siroya and Prof Manju Mandot 1.1 Introduction 2 1.2 Need for Artificial Intelligence 2 1.3 Artificial Intelligence in Cyber Security 3 1.3.1 Multi-Layered Security System Design 3 1.3.2 Traditional Security Approach and AI 4 1.4 Related Work 5 1.4.1 Literature Review 5 1.4.2 Corollary 6 1.5 Proposed Work 6 1.5.1 System Architecture 7 1.5.2 Future Scope 7 1.6 Conclusion 7 References 8 2 Privacy Preserving Using Data Mining 11 Chitra Jalota and Dr. Rashmi Agrawal 2.1 Introduction 11 2.2 Data Mining Techniques and Their Role in Classification and Detection 14 2.3 Clustering 19 2.4 Privacy Preserving Data Mining (PPDM) 21 2.5 Intrusion Detection Systems (IDS) 22 2.5.1 Types of IDS 23 2.5.1.1 Network-Based IDS 23 2.5.1.2 Host-Based IDS 24 2.5.1.3 Hybrid IDS 25 2.6 Phishing Website Classification 26 2.7 Attacks by Mitigating Code Injection 27 2.7.1 Code Injection and Its Categories 27 2.8 Conclusion 28 References 29 3 Role of Artificial Intelligence in Cyber Security and Security Framework 33 Shweta Sharma 3.1 Introduction 34 3.2 AI for Cyber Security 36 3.3 Uses of Artificial Intelligence in Cyber Security 38 3.4 The Role of AI in Cyber Security 40 3.4.1 Simulated Intelligence Can Distinguish Digital Assaults 41 3.4.2 Computer-Based Intelligence Can Forestall Digital Assaults 42 3.4.3 Artificial Intelligence and Huge Scope Cyber Security 42 3.4.4 Challenges and Promises of Artificial Intelligence in Cyber Security 43 3.4.5 Present-Day Cyber Security and its Future with Simulated Intelligence 44 3.4.6 Improved Cyber Security with Computer-Based Intelligence and AI (ML) 45 3.4.7 AI Adopters Moving to Make a Move 45 3.5 AI Impacts on Cyber Security 46 3.6 The Positive Uses of AI Based for Cyber Security 48 3.7 Drawbacks and Restrictions of Using Computerized Reasoning For Digital Security 49 3.8 Solutions to Artificial Intelligence Confinements 50 3.9 Security Threats of Artificial Intelligence 51 3.10 Expanding Cyber Security Threats with Artificial Consciousness 52 3.11 Artificial Intelligence in Cybersecurity – Current Use-Cases and Capabilities 55 3.11.1 AI for System Danger Distinguishing Proof 56 3.11.2 The Common Fit for Artificial Consciousness in Cyber Security 56 3.11.3 Artificial Intelligence for System Danger ID 57 3.11.4 Artificial Intelligence Email Observing 58 3.11.5 Simulated Intelligence for Battling Artificial Intelligence Dangers 58 3.11.6 The Fate of Computer-Based Intelligence in Cyber Security 59 3.12 How to Improve Cyber Security for Artificial Intelligence 60 3.13 Conclusion 61 References 62 4 Botnet Detection Using Artificial Intelligence 65 Astha Parihar and Prof. Neeraj Bhargava 4.1 Introduction to Botnet 66 4.2 Botnet Detection 67 4.2.1 Host-Centred Detection (HCD) 68 4.2.2 Honey Nets-Based Detection (HNBD) 69 4.2.3 Network-Based Detection (NBD) 69 4.3 Botnet Architecture 69 4.3.1 Federal Model 70 4.3.1.1 IBN-Based Protocol 71 4.3.1.2 HTTP-Based Botnets 71 4.3.2 Devolved Model 71 4.3.3 Cross Model 72 4.4 Detection of Botnet 73 4.4.1 Perspective of Botnet Detection 73 4.4.2 Detection (Disclosure) Technique 73 4.4.3 Region of Tracing 74 4.5 Machine Learning 74 4.5.1 Machine Learning Characteristics 74 4.6 A Machine Learning Approach of Botnet Detection 75 4.7 Methods of Machine Learning Used in Botnet Exposure 76 4.7.1 Supervised (Administrated) Learning 76 4.7.1.1 Appearance of Supervised Learning 77 4.7.2 Unsupervised Learning 78 4.7.2.1 Role of Unsupervised Learning 79 4.8 Problems with Existing Botnet Detection Systems 80 4.9 Extensive Botnet Detection System (EBDS) 81 4.10 Conclusion 83 References 84 5 Spam Filtering Using AI 87 Yojna Khandelwal and Dr. Ritu Bhargava 5.1 Introduction 87 5.1.1 What is SPAM? 87 5.1.2 Purpose of Spamming 88 5.1.3 Spam Filters Inputs and Outputs 88 5.2 Content-Based Spam Filtering Techniques 89 5.2.1 Previous Likeness–Based Filters 89 5.2.2 Case-Based Reasoning Filters 89 5.2.3 Ontology-Based E-Mail Filters 90 5.2.4 Machine-Learning Models 90 5.2.4.1 Supervised Learning 90 5.2.4.2 Unsupervised Learning 90 5.2.4.3 Reinforcement Learning 91 5.3 Machine Learning–Based Filtering 91 5.3.1 Linear Classifiers 91 5.3.2 Naïve Bayes Filtering 92 5.3.3 Support Vector Machines 94 5.3.4 Neural Networks and Fuzzy Logics–Based Filtering 94 5.4 Performance Analysis 97 5.5 Conclusion 97 References 98 6 Artificial Intelligence in the Cyber Security Environment 101 Jaya Jain 6.1 Introduction 102 6.2 Digital Protection and Security Correspondences Arrangements 104 6.2.1 Operation Safety and Event Response 105 6.2.2 AI2 105 6.2.2.1 CylanceProtect 105 6.3 Black Tracking 106 6.3.1 Web Security 107 6.3.1.1 Amazon Macie 108 6.4 Spark Cognition Deep Military 110 6.5 The Process of Detecting Threats 111 6.6 Vectra Cognito Networks 112 6.7 Conclusion 115 References 115 7 Privacy in Multi-Tenancy Frameworks Using AI 119 Shweta Solanki 7.1 Introduction 119 7.2 Framework of Multi-Tenancy 120 7.3 Privacy and Security in Multi-Tenant Base System Using AI 122 7.4 Related Work 125 7.5 Conclusion 125 References 126 8 Biometric Facial Detection and Recognition Based on ILPB and SVM 129 Shubhi Srivastava, Ankit Kumar and Shiv Prakash 8.1 Introduction 129 8.1.1 Biometric 131 8.1.2 Categories of Biometric 131 8.1.2.1 Advantages of Biometric 132 8.1.3 Significance and Scope 132 8.1.4 Biometric Face Recognition 132 8.1.5 Related Work 136 8.1.6 Main Contribution 136 8.1.7 Novelty Discussion 137 8.2 The Proposed Methodolgy 139 8.2.1 Face Detection Using Haar Algorithm 139 8.2.2 Feature Extraction Using ILBP 141 8.2.3 Dataset 143 8.2.4 Classification Using SVM 143 8.3 Experimental Results 145 8.3.1 Face Detection 146 8.3.2 Feature Extraction 146 8.3.3 Recognize Face Image 147 8.4 Conclusion 151 References 152 9 Intelligent Robot for Automatic Detection of Defects in Pre-Stressed Multi-Strand Wires and Medical Gas Pipe Line System Using ANN and IoT 155 S K Rajesh Kanna, O. Pandithurai, N. Anand, P. Sethuramalingam and Abdul Munaf 9.1 Introduction 156 9.2 Inspection System for Defect Detection 158 9.3 Defect Recognition Methodology 162 9.4 Health Care MGPS Inspection 165 9.5 Conclusion 168 References 169 10 Fuzzy Approach for Designing Security Framework 173 Kapil Chauhan 10.1 Introduction 173 10.2 Fuzzy Set 177 10.3 Planning for a Rule-Based Expert System for Cyber Security 185 10.3.1 Level 1: Defining Cyber Security Expert System Variables 185 10.3.2 Level 2: Information Gathering for Cyber Terrorism 185 10.3.3 Level 3: System Design 186 10.3.4 Level 4: Rule-Based Model 187 10.4 Digital Security 188 10.4.1 Cyber-Threats 188 10.4.2 Cyber Fault 188 10.4.3 Different Types of Security Services 189 10.5 Improvement of Cyber Security System (Advance) 190 10.5.1 Structure 190 10.5.2 Cyber Terrorism for Information/Data Collection 191 10.6 Conclusions 191 References 192 11 Threat Analysis Using Data Mining Technique 197 Riddhi Panchal and Binod Kumar 11.1 Introduction 198 11.2 Related Work 199 11.3 Data Mining Methods in Favor of Cyber-Attack Detection 201 11.4 Process of Cyber-Attack Detection Based on Data Mining 204 11.5 Conclusion 205 References 205 12 Intrusion Detection Using Data Mining 209 Astha Parihar and Pramod Singh Rathore 12.1 Introduction 209 12.2 Essential Concept 210 12.2.1 Intrusion Detection System 211 12.2.2 Categorization of IDS 212 12.2.2.1 Web Intrusion Detection System (WIDS) 213 12.2.2.2 Host Intrusion Detection System (HIDS) 214 12.2.2.3 Custom-Based Intrusion Detection System (CIDS) 215 12.2.2.4 Application Protocol-Based Intrusion Detection System (APIDS) 215 12.2.2.5 Hybrid Intrusion Detection System 216 12.3 Detection Program 216 12.3.1 Misuse Detection 217 12.3.1.1 Expert System 217 12.3.1.2 Stamp Analysis 218 12.3.1.3 Data Mining 220 12.4 Decision Tree 221 12.4.1 Classification and Regression Tree (CART) 222 12.4.2 Iterative Dichotomise 3 (ID3) 222 12.4.3 C 4.5 223 12.5 Data Mining Model for Detecting the Attacks 223 12.5.1 Framework of the Technique 224 12.6 Conclusion 226 References 226 13 A Maize Crop Yield Optimization and Healthcare Monitoring Framework Using Firefly Algorithm through IoT 229 S K Rajesh Kanna, V. Nagaraju, D. Jayashree, Abdul Munaf and M. Ashok 13.1 Introduction 230 13.2 Literature Survey 231 13.3 Experimental Framework 232 13.4 Healthcare Monitoring 237 13.5 Results and Discussion 240 13.6 Conclusion 242 References 243 14 Vision-Based Gesture Recognition: A Critical Review 247 Neela Harish, Praveen, Prasanth, Aparna and Athaf 14.1 Introduction 247 14.2 Issues in Vision-Based Gesture Recognition 248 14.2.1 Based on Gestures 249 14.2.2 Based on Performance 249 14.2.3 Based on Background 249 14.3 Step-by-Step Process in Vision-Based 249 14.3.1 Sensing 251 14.3.2 Preprocessing 252 14.3.3 Feature Extraction 252 14.4 Classification 253 14.5 Literature Review 254 14.6 Conclusion 258 References 258 15 SPAM Filtering Using Artificial Intelligence 261 Abha Jain 15.1 Introduction 261 15.2 Architecture of Email Servers and Email Processing Stages 265 15.2.1 Architecture - Email Spam Filtering 265 15.2.1.1 Spam Filter - Gmail 266 15.2.1.2 Mail Filter Spam - Yahoo 266 15.2.1.3 Email Spam Filter - Outlook 267 15.2.2 Email Spam Filtering - Process 267 15.2.2.1 Pre-Handling 268 15.2.2.2 Taxation 268 15.2.2.3 Election of Features 268 15.2.3 Freely Available Email Spam Collection 269 15.3 Execution Evaluation Measures 269 15.4 Classification - Machine Learning Technique for Email Spam 275 15.4.1 Flock Technique - Clustering 275 15.4.2 Naïve Bayes Classifier 276 15.4.3 Neural Network 279 15.4.4 Firefly Algorithm 282 15.4.5 Fuzzy Set Classifiers 283 15.4.6 Support Vector Machine 284 15.4.7 Decision Tree 286 15.4.7.1 NBTree Classifier 286 15.4.7.2 C4.5/J48 Decision Tree Algorithm 287 15.4.7.3 Logistic Version Tree Induction (LVT) 287 15.4.8 Ensemble Classifiers 288 15.4.9 Random Forests (RF) 289 15.5 Conclusion 290 References 290 Index 295