Investigative Data Mining for Security and Criminal Detection (eBook)

Cover 1
Copyright Page 7
Contents 10
Introduction 16
Chapter 1. Precrime Data Mining 18
1.1 Behavioral Profiling 18
1.2 Rivers of Scraps 19
1.3 Data Mining 20
1.4 Investigative Data Warehousing 21
1.5 Link Analysis 22
1.6 Software Agents 23
1.7 Text Mining 25
1.8 Neural Networks 26
1.9 Machine Learning 28
1.10 Precrime 31
1.11 September 11, 2001 32
1.12 Criminal Analysis and Data Mining 32
1.13 Profiling via Pattern Recognition 36
1.14 Calibrating Crime 39
1.15 Clustering Burglars: A Case Study 41
1.16 The Future 54
1.17 Bibliography 55
Chapter 2. Investigative Data Warehousing 56
2.1 Relevant Data 56
2.2 Data Testing 57
2.3 The Data Warehouse 57
2.4 Demographic Data 59
2.5 Real Estate and Auto Data 63
2.6 Credit Data 63
2.7 Criminal Data 64
2.8 Government Data 72
2.9 Internet Data 72
2.10 XML 76
2.11 Data Preparation 78
2.12 Interrogating the Data 80
2.13 Data Integration 81
2.14 Security and Privacy 82
2.15 ChoicePoint: A Case Study 83
2.16 Tools for Data Preparation 85
2.17 Standardizing Criminal Data 89
2.18 Bibliography 91
Chapter 3. Link Analysis: Visualizing Associations 92
3.1 How Link Analysis Works 92
3.2 What Can Link Analysis Do? 92
3.3 What Is Link Analysis? 93
3.4 Using Link Analysis Networks 94
3.5 Fighting Wireless Fraud with Link Analysis: A Case Study 95
3.6 Types of Link Analysis 97
3.7 Combating Drug Trafficking in Florida with Link Analysis: A Case Study 98
3.8 Link Analysis Applications 99
3.9 Focusing on Money Laundering via Link Analysis: A Case Study 101
3.10 Link Analysis Limitations 102
3.11 Link Analysis Tools 105
3.12 Bibliography 121
Chapter 4. Intelligent Agents: Software Detectives 124
4.1 What Can Agents Do? 124
4.2 What Is an Agent? 125
4.3 Agent Features 126
4.4 Why Are Agents Important? 128
4.5 Open Sources Agents 129
4.6 Secured Sources Agents 130
4.7 How Agents Work 130
4.8 How Agents Reason 131
4.9 Intelligent Agents 133
4.10 A Bio-Surveillance Agent: A Case Study 134
4.11 Data Mining Agents 137
4.12 Agents Tools 138
4.13 Bibliography 140
Chapter 5. Text Mining: Clustering Concepts 142
5.1 What Is Text Mining? 142
5.2 How Does Text Mining Work? 143
5.3 Text Mining Applications 144
5.4 Searching for Clues in Aviation Crashes: A Case Study 145
5.5 Clustering News Stories: A Case Study 147
5.6 Text Mining for Deception 149
5.7 Text Mining Threats 155
5.8 Text Mining Tools 158
5.9 Bibliography 174
Chapter 6. Neural Networks: Classifying Patterns 176
6.1 What Do Neural Networks Do? 176
6.2 What Is a Neural Network? 177
6.3 How Do Neural Networks Work? 178
6.4 Types of Network Architectures 179
6.5 Using Neural Networks 180
6.6 Why Use Neural Networks? 181
6.7 Attrasoft Facial Recognition Classifications System: A Demonstration 182
6.8 Chicago Internal Affairs Uses Neural Network: A Case Study 184
6.9 Clustering Border Smugglers with a SOM: A Demonstration 186
6.10 Neural Network Chromatogram Retrieval System: A Case Study 189
6.11 Neural Network Investigative Applications 195
6.12 Modus Operandi Modeling of Group Offending: A Case Study 196
6.13 False Positives 212
6.14 Neural Network Tools 213
6.15 Bibliography 221
Chapter 7. Machine Learning: Developing Profiles 222
7.1 What Is Machine Learning? 222
7.2 How Machine Learning Works 223
7.3 Decision Trees 224
7.4 Rules Predicting Crime 225
7.5 Machine Learning at the Border: A Case Study 227
7.6 Extrapolating Military Data: A Case Study 229
7.7 Detecting Suspicious Government Financial Transactions: A Case Study 230
7.8 Machine-Learning Criminal Patterns 236
7.9 The Decision Tree Tools 238
7.10 The Rule-Extracting Tools 246
7.11 Machine-Learning Software Suites 250
7.12 Bibliography 265
Chapter 8. NetFraud: A Case Study 266
8.1 Fraud Detection in Real Time 266
8.2 Fraud Migrates On-line 267
8.3 Credit-Card Fraud 267
8.4 The Fraud Profile 268
8.5 The Risk Scores 269
8.6 Transactional Data 270
8.7 Common-Sense Rules 270
8.8 Auction Fraud 271
8.9 NetFraud 273
8.10 Fraud-Detection Services 274
8.11 Building a Fraud-Detection System 275
8.12 Extracting Data Samples 276
8.13 Enhancing the Data 276
8.14 Assembling the Mining Tools 278
8.15 A View of Fraud 278
8.16 Clustering Fraud 279
8.17 Detecting Fraud 281
8.18 NetFraud in the United Kingdom: A Statistical Study 283
8.19 Machine-Learning and Fraud 284
8.20 The Fraud Ensemble 287
8.21 The Outsourcing Option 288
8.22 The Hybrid Solution 289
8.23 Bibliography 290
Chapter 9. Criminal Patterns: Detection Techniques 292
9.1 Patterns and Outliers 292
9.2 Money As Data 293
9.3 Financial Crime MOs 294
9.4 Money Laundering 296
9.5 Insurance Crimes 298
9.6 Death Claims That Did Not Add Up: A Case Study 304
9.7 Telecommunications Crime MOs 305
9.8 Identity Crimes 308
9.9 A Data Mining Methodology for Detecting Crimes 310
9.10 Ensemble Mechanisms for Crime Detection 313
9.11 Bibliography 316
Chapter 10. Intrusion Detection: Techniques and Systems 318
10.1 Cybercrimes 318
10.2 Intrusion MOs 319
10.3 Intrusion Patterns 326
10.4 Anomaly Detection 326
10.5 Misuse Detection 327
10.6 Intrusion Detection Systems 327
10.7 Data Mining for Intrusion Detection: A Case Study from the Mitre Corporation 330
10.8 Types of IDSs 335
10.9 Misuse IDSs 335
10.10 Anomaly IDSs 336
10.11 Multiple-Based IDSs 338
10.12 Data Mining IDSs 338
10.13 Advanced IDSs 340
10.14 Forensic Considerations 341
10.15 Early Warning Systems 342
10.16 Internet Resources 343
10.17 Bibliography 343
Chapter 11. The Entity Validation System (EVS): A Conceptual Architecture 344
11.1 The Grid 344
11.2 GRASP 345
11.3 Access Versus Storage 345
11.4 The Virtual Federation 346
11.5 Web Services 347
11.6 The Software Glue 348
11.7 The Envisioned EVS 350
11.8 Needles in Moving Haystacks 351
11.9 Tracking Identities 353
11.10 The AI Apprentice 354
11.11 Incremental Composites 355
11.12 Machine Man 357
11.13 Bibliography 358
Chapter 12. Mapping Crime: Clustering Case Work 360
12.1 Crime Maps 360
12.2 Interactive Crime GIS 362
12.3 Crime Clusters 363
12.4 Modeling the Behavior of Offenders Who Commit Serious Sexual Assaults: A Case Study 365
12.5 Decomposing Signatures Software 380
12.6 Computer Aided Tracking and Characterization of Homicides and Sexual Assaults (CATCH) 381
12.7 Forensic Data Mining 392
12.8 Alien Intelligence 393
12.9 Bibliography 395
A: 1,000 Online Sources for the Investigative Data Miner 396
B: Intrusion Detection Systems (IDS) Products, Services, Freeware, and Projects 432
C: Intrusion Detection Glossary 436
D: Investigative Data Mining Products and Services 448
Index 452