Intelligent Data Analytics for Terror Threat Prediction: Architectures, Methodologies, Techniques, and Applications

Intelligent data analytics for terror threat prediction is an emerging field of research at the intersection of information science and computer science, bringing with it a new era of tremendous opportunities and challenges due to plenty of easily available criminal data for further analysis. This book provides innovative insights that will help obtain interventions to undertake emerging dynamic scenarios of criminal activities. Furthermore, it presents emerging issues, challenges and management strategies in public safety and crime control development across various domains. The book will play a vital role in improvising human life to a great extent. Researchers and practitioners working in the fields of data mining, machine learning and artificial intelligence will greatly benefit from this book, which will be a good addition to the state-of-the-art approaches collected for intelligent data analytics. It will also be very beneficial for those who are new to the field and need to quickly become acquainted with the best performing methods. With this book they will be able to compare different approaches and carry forward their research in the most important areas of this field, which has a direct impact on the betterment of human life by maintaining the security of our society. No other book is currently on the market which provides such a good collection of state-of-the-art methods for intelligent data analytics-based models for terror threat prediction, as intelligent data analytics is a newly emerging field and research in data mining and machine learning is still in the early stage of development.

Table of Contents:
Preface xv 1 Rumor Detection and Tracing its Source to Prevent Cyber-Crimes on Social Media 1 Ravi Kishore Devarapalli and Anupam Biswas 1.1 Introduction 2 1.2 Social Networks 4 1.2.1 Types of Social Networks 4 1.3 What is Cyber-Crime? 7 1.3.1 Definition 7 1.3.2 Types of Cyber-Crimes 7 1.3.2.1 Hacking 7 1.3.2.2 Cyber Bullying 7 1.3.2.3 Buying Illegal Things 8 1.3.2.4 Posting Videos of Criminal Activity 8 1.3.3 Cyber-Crimes on Social Networks 8 1.4 Rumor Detection 9 1.4.1 Models 9 1.4.1.1 Naïve Bayes Classifier 10 1.4.1.2 Support Vector Machine 13 1.4.2 Combating Misinformation on Instagram 14 1.5 Factors to Detect Rumor Source 15 1.5.1 Network Structure 15 1.5.1.1 Network Topology 16 1.5.1.2 Network Observation 16 1.5.2 Diffusion Models 18 1.5.2.1 SI Model 18 1.5.2.2 SIS Model 19 1.5.2.3 SIR Model 19 1.5.2.4 SIRS Model 20 1.5.3 Centrality Measures 21 1.5.3.1 Degree Centrality 21 1.5.3.2 Closeness Centrality 21 1.5.3.3 Betweenness Centrality 22 1.6 Source Detection in Network 22 1.6.1 Single Source Detection 23 1.6.1.1 Network Observation 23 1.6.1.2 Query-Based Approach 25 1.6.1.3 Anti-Rumor-Based Approach 26 1.6.2 Multiple Source Detection 26 1.7 Conclusion 27 References 28 2 Internet of Things (IoT) and Machine to Machine (M2M) Communication Techniques for Cyber Crime Prediction 31 Jaiprakash Narain Dwivedi 2.1 Introduction 32 2.2 Advancement of Internet 33 2.3 Internet of Things (IoT) and Machine to Machine (M2M) Communication 34 2.4 A Definition of Security Frameworks 38 2.5 M2M Devices and Smartphone Technology 39 2.6 Explicit Hazards to M2M Devices Declared by Smartphone Challenges 41 2.7 Security and Privacy Issues in IoT 43 2.7.1 Dynamicity and Heterogeneity 43 2.7.2 Security for Integrated Operational World with Digital World 44 2.7.3 Information Safety with Equipment Security 44 2.7.4 Data Source Information 44 2.7.5 Information Confidentiality 44 2.7.6 Trust Arrangement 44 2.8 Protection in Machine to Machine Communication 48 2.9 Use Cases for M2M Portability 52 2.10 Conclusion 53 References 54 3 Crime Predictive Model Using Big Data Analytics 57 Hemanta Kumar Bhuyan and Subhendu Kumar Pani 3.1 Introduction 58 3.1.1 Geographic Information System (GIS) 59 3.2 Crime Data Mining 60 3.2.1 Different Methods for Crime Data Analysis 62 3.3 Visual Data Analysis 63 3.4 Technological Analysis 65 3.4.1 Hadoop and MapReduce 65 3.4.1.1 Hadoop Distributed File System (HDFS) 65 3.4.1.2 MapReduce 65 3.4.2 Hive 67 3.4.2.1 Analysis of Crime Data using Hive 67 3.4.2.2 Data Analytic Module With Hive 68 3.4.3 Sqoop 68 3.4.3.1 Pre-Processing and Sqoop 68 3.4.3.2 Data Migration Module With Sqoop 68 3.4.3.3 Partitioning 68 3.4.3.4 Bucketing 68 3.4.3.5 R-Tool Analyse Crime Data 69 3.4.3.6 Correlation Matrix 69 3.5 Big Data Framework 69 3.6 Architecture for Crime Technical Model 72 3.7 Challenges 73 3.8 Conclusions 74 References 75 4 The Role of Remote Sensing and GIS in Military Strategy to Prevent Terror Attacks 79 Sushobhan Majumdar 4.1 Introduction 80 4.2 Database and Methods 81 4.3 Discussion and Analysis 82 4.4 Role of Remote Sensing and GIS 83 4.5 Cartographic Model 83 4.5.1 Spatial Data Management 85 4.5.2 Battlefield Management 85 4.5.3 Terrain Analysis 86 4.6 Mapping Techniques Used for Defense Purposes 87 4.7 Naval Operations 88 4.7.1 Air Operations 89 4.7.2 GIS Potential in Military 89 4.8 Future Sphere of GIS in Military Science 89 4.8.1 Defense Site Management 90 4.8.2 Spatial Data Management 90 4.8.3 Intelligence Capability Approach 90 4.8.4 Data Converts Into Information 90 4.8.5 Defense Estate Management 91 4.9 Terrain Evolution 91 4.9.1 Problems Regarding the Uses of Remote Sensing and GIS 91 4.9.2 Recommendations 92 4.10 Conclusion 92 References 93 5 Text Mining for Secure Cyber Space 95 Supriya Raheja and Geetika Munjal 5.1 Introduction 95 5.2 Literature Review 97 5.2.1 Text Mining With Latent Semantic Analysis 100 5.3 Latent Semantic Analysis 101 5.4 Proposed Work 102 5.5 Detailed Work Flow of Proposed Approach 104 5.5.1 Defining the Stop Words 106 5.5.2 Stemming 107 5.5.3 Proposed Algorithm: A Hybrid Approach 109 5.6 Results and Discussion 111 5.6.1 Analysis Using Hybrid Approach 111 5.7 Conclusion 115 References 115 6 Analyses on Artificial Intelligence Framework to Detect Crime Pattern 119 R. Arshath Raja, N. Yuvaraj and N.V. Kousik 6.1 Introduction 120 6.2 Related Works 121 6.3 Proposed Clustering for Detecting Crimes 122 6.3.1 Data Pre-Processing 123 6.3.2 Object-Oriented Model 124 6.3.3 MCML Classification 124 6.3.4 GAA 124 6.3.5 Consensus Clustering 124 6.4 Performance Evaluation 124 6.4.1 Precision 125 6.4.2 Sensitivity 125 6.4.3 Specificity 131 6.4.4 Accuracy 131 6.5 Conclusions 131 References 132 7 A Biometric Technology-Based Framework for Tackling and Preventing Crimes 133 Ebrahim A.M. Alrahawe, Vikas T. Humbe and G.N. Shinde 7.1 Introduction 134 7.2 Biometrics 135 7.2.1 Biometric Systems Technologies 137 7.2.2 Biometric Recognition Framework 141 7.2.3 Biometric Applications/Usages 142 7.3 Surveillance Systems (CCTV) 144 7.3.1 CCTV Goals 146 7.3.2 CCTV Processes 146 7.3.3 Fusion of Data From Multiple Cameras 149 7.3.4 Expanding the Use of CCTV 149 7.3.5 CCTV Effectiveness 150 7.3.6 CCTV Limitations 150 7.3.7 Privacy and CCTV 150 7.4 Legality to Surveillance and Biometrics vs. Privacy and Human Rights 151 7.5 Proposed Work (Biometric-Based CCTV System) 153 7.5.1 Biometric Surveillance System 154 7.5.1.1 System Component and Flow Diagram 154 7.5.2 Framework 156 7.6 Conclusion 158 References 159 8 Rule-Based Approach for Botnet Behavior Analysis 161 Supriya Raheja, Geetika Munjal, Jyoti Jangra and Rakesh Garg 8.1 Introduction 161 8.2 State-of-the-Art 163 8.3 Bots and Botnets 166 8.3.1 Botnet Life Cycle 166 8.3.2 Botnet Detection Techniques 167 8.3.3 Communication Architecture 168 8.4 Methodology 171 8.5 Results and Analysis 175 8.6 Conclusion and Future Scope 177 References 177 9 Securing Biometric Framework with Cryptanalysis 181 Abhishek Goel, Siddharth Gautam, Nitin Tyagi, Nikhil Sharma and Martin Sagayam 9.1 Introduction 182 9.2 Basics of Biometric Systems 184 9.2.1 Face 185 9.2.2 Hand Geometry 186 9.2.3 Fingerprint 187 9.2.4 Voice Detection 187 9.2.5 Iris 188 9.2.6 Signature 189 9.2.7 Keystrokes 189 9.3 Biometric Variance 192 9.3.1 Inconsistent Presentation 192 9.3.2 Unreproducible Presentation 192 9.3.3 Fault Signal/Representational Accession 193 9.4 Performance of Biometric System 193 9.5 Justification of Biometric System 195 9.5.1 Authentication (“Is this individual really the authenticate user or not?”) 195 9.5.2 Recognition (“Is this individual in the database?”) 196 9.5.3 Concealing (“Is this a needed person?”) 196 9.6 Assaults on a Biometric System 196 9.6.1 Zero Effort Attacks 197 9.6.2 Adversary Attacks 198 9.6.2.1 Circumvention 198 9.6.2.2 Coercion 198 9.6.2.3 Repudiation 198 9.6.2.4 DoB (Denial of Benefit) 199 9.6.2.5 Collusion 199 9.7 Biometric Cryptanalysis: The Fuzzy Vault Scheme 199 9.8 Conclusion & Future Work 203 References 205 10 The Role of Big Data Analysis in Increasing the Crime Prediction and Prevention Rates 209 Galal A. AL-Rummana, Abdulrazzaq H. A. Al-Ahdal and G.N. Shinde 10.1 Introduction: An Overview of Big Data and Cyber Crime 210 10.2 Techniques for the Analysis of BigData 211 10.3 Important Big Data Security Techniques 216 10.4 Conclusion 219 References 219 11 Crime Pattern Detection Using Data Mining 221 Dipalika Das and Maya Nayak 11.1 Introduction 221 11.2 Related Work 222 11.3 Methods and Procedures 224 11.4 System Analysis 227 11.5 Analysis Model and Architectural Design 230 11.6 Several Criminal Analysis Methods in Use 233 11.7 Conclusion and Future Work 235 References 235 12 Attacks and Security Measures in Wireless Sensor Network 237 Nikhil Sharma, Ila Kaushik, Vikash Kumar Agarwal, Bharat Bhushan and Aditya Khamparia 12.1 Introduction 238 12.2 Layered Architecture of WSN 239 12.2.1 Physical Layer 239 12.2.2 Data Link Layer 239 12.2.3 Network Layer 240 12.2.4 Transport Layer 240 12.2.5 Application Layer 241 12.3 Security Threats on Different Layers in WSN 241 12.3.1 Threats on Physical Layer 241 12.3.1.1 Eavesdropping Attack 241 12.3.1.2 Jamming Attack 242 12.3.1.3 Imperil or Compromised Node Attack 242 12.3.1.4 Replication Node Attack 242 12.3.2 Threats on Data Link Layer 242 12.3.2.1 Collision Attack 243 12.3.2.2 Denial of Service (DoS) Attack 243 12.3.2.3 Intelligent Jamming Attack 243 12.3.3 Threats on Network Layer 243 12.3.3.1 Sybil Attack 243 12.3.3.2 Gray Hole Attack 243 12.3.3.3 Sink Hole Attack 244 12.3.3.4 Hello Flooding Attack 244 12.3.3.5 Spoofing Attack 244 12.3.3.6 Replay Attack 244 12.3.3.7 Black Hole Attack 244 12.3.3.8 Worm Hole Attack 245 12.3.4 Threats on Transport Layer 245 12.3.4.1 De-Synchronization Attack 245 12.3.4.2 Flooding Attack 245 12.3.5 Threats on Application Layer 245 12.3.5.1 Malicious Code Attack 245 12.3.5.2 Attack on Reliability 246 12.3.6 Threats on Multiple Layer 246 12.3.6.1 Man-in-the-Middle Attack 246 12.3.6.2 Jamming Attack 246 12.3.6.3 Dos Attack 246 12.4 Threats Detection at Various Layers in WSN 246 12.4.1 Threat Detection on Physical Layer 247 12.4.1.1 Compromised Node Attack 247 12.4.1.2 Replication Node Attack 247 12.4.2 Threat Detection on Data Link Layer 247 12.4.2.1 Denial of Service Attack 247 12.4.3 Threat Detection on Network Layer 248 12.4.3.1 Black Hole Attack 248 12.4.3.2 Worm Hole Attack 248 12.4.3.3 Hello Flooding Attack 249 12.4.3.4 Sybil Attack 249 12.4.3.5 Gray Hole Attack 250 12.4.3.6 Sink Hole Attack 250 12.4.4 Threat Detection on the Transport Layer 251 12.4.4.1 Flooding Attack 251 12.4.5 Threat Detection on Multiple Layers 251 12.4.5.1 Jamming Attack 251 12.5 Various Parameters for Security Data Collection in WSN 252 12.5.1 Parameters for Security of Information Collection 252 12.5.1.1 Information Grade 252 12.5.1.2 Efficacy and Proficiency 253 12.5.1.3 Reliability Properties 253 12.5.1.4 Information Fidelity 253 12.5.1.5 Information Isolation 254 12.5.2 Attack Detection Standards in WSN 254 12.5.2.1 Precision 254 12.5.2.2 Germane 255 12.5.2.3 Extensibility 255 12.5.2.4 Identifiability 255 12.5.2.5 Fault Forbearance 255 12.6 Different Security Schemes in WSN 256 12.6.1 Clustering-Based Scheme 256 12.6.2 Cryptography-Based Scheme 256 12.6.3 Cross-Checking-Based Scheme 256 12.6.4 Overhearing-Based Scheme 257 12.6.5 Acknowledgement-Based Scheme 257 12.6.6 Trust-Based Scheme 257 12.6.7 Sequence Number Threshold-Based Scheme 258 12.6.8 Intrusion Detection System-Based Scheme 258 12.6.9 Cross-Layer Collaboration-Based Scheme 258 12.7 Conclusion 264 References 264 13 Large Sensing Data Flows Using Cryptic Techniques 269 Hemanta Kumar Bhuyan 13.1 Introduction 270 13.2 Data Flow Management 271 13.2.1 Data Flow Processing 271 13.2.2 Stream Security 272 13.2.3 Data Privacy and Data Reliability 272 13.2.3.1 Security Protocol 272 13.3 Design of Big Data Stream 273 13.3.1 Data Stream System Architecture 273 13.3.1.1 Intrusion Detection Systems (IDS) 274 13.3.2 Malicious Model 275 13.3.3 Threat Approaches for Attack Models 276 13.4 Utilization of Security Methods 277 13.4.1 System Setup 278 13.4.2 Re-Keying 279 13.4.3 New Node Authentication 279 13.4.4 Cryptic Techniques 280 13.5 Analysis of Security on Attack 280 13.6 Artificial Intelligence Techniques for Cyber Crimes 281 13.6.1 Cyber Crime Activities 282 13.6.2 Artificial Intelligence for Intrusion Detection 282 13.6.3 Features of an IDPS 284 13.7 Conclusions 284 References 285 14 Cyber-Crime Prevention Methodology 291 Chandra Sekhar Biswal and Subhendu Kumar Pani 14.1 Introduction 292 14.1.1 Evolution of Cyber Crime 294 14.1.2 Cybercrime can be Broadly Defined as Two Types 296 14.1.3 Potential Vulnerable Sectors of Cybercrime 296 14.2 Credit Card Frauds and Skimming 297 14.2.1 Matrimony Fraud 297 14.2.2 Juice Jacking 298 14.2.3 Technicality Behind Juice Jacking 299 14.3 Hacking Over Public WiFi or the MITM Attacks 299 14.3.1 Phishing 300 14.3.2 Vishing/Smishing 302 14.3.3 Session Hijacking 303 14.3.4 Weak Session Token Generation/Predictable Session Token Generation 304 14.3.5 IP Spoofing 304 14.3.6 Cross-Site Scripting (XSS) Attack 305 14.4 SQLi Injection 306 14.5 Denial of Service Attack 307 14.6 Dark Web and Deep Web Technologies 309 14.6.1 The Deep Web 309 14.6.2 The Dark Web 310 14.7 Conclusion 311 References 312 Index 313