这个好像也没有噢......

Contents
Part I Research Framework: Overview and Introduction
1 Dark Web Research Overview . 3
1 Introduction ..... 3
1.1 Web Sites... 3
1.2 Forums ... 4
1.3 Blogs, Social Networking Sites, and Virtual Worlds .. 4
1.4 Videos and Multimedia Content .... 4
2 Computational Techniques (Data Mining, Text Mining,
and Web Mining) .. 4
2.1 Dark Web Collection . 5
2.2 Dark Web Analysis and Visualization . 5
3 Dark Web Project Structure and Resources .. 7
3.1 Team Members (Selected) .. 8
3.2 Press Coverage and Interest ... 8
3.3 The IEEE Intelligence and Security
Informatics Conference .... 9
3.4 Dark Web Publications. 10
3.5 Dark Web Project Funding and Acknowledgments .... 16
4 Partnership Acknowledgments .... 17
Reference ... 18
2 Intelligence and Security Informatics (ISI):
Research Framework ... 19
1 Information Technology and National Security ... 19
1.1 Problems and Challenges .... 21
1.2 Intelligence and Security Informatics Versus
Biomedical Informatics: Emergence of a Discipline .. 22
1.3 Research Opportunities .... 24
xviii Contents
2 ISI Research Framework .... 24
2.1 Caveats for Data Mining ..... 27
2.2 Domestic Security, Civil Liberties,
and Knowledge Discovery .. 28
2.3 Research Opportunities .... 29
References ..... 29
3 Terrorism Informatics ..... 31
1 Introduction ..... 31
2 Terrorism and the Internet .. 31
3 Terrorism Research Centers and Resources .. 33
3.1 Think Tanks and Intelligence Resources .... 33
3.2 Terrorism Databases and Online Resources... 34
3.3 Higher Education Research Institutes .. 39
4 Conclusions ..... 41
References ..... 41
Part II Dark Web Research: Computational
Approach and Techniques
4 Forum Spidering .... 45
1 Introduction ..... 45
2 Related Work: Focused and Hidden Web Crawlers ... 46
2.1 Accessibility . 47
2.2 Collection Type ... 47
2.3 Content Richness ... 48
2.4 URL Ordering Features .... 48
2.5 URL Ordering Techniques .. 49
2.6 Collection Update Procedure ...... 50
2.7 Summary of Previous Research ..... 50
3 Research Gaps and Questions ... 52
3.1 Focused Crawling of the Hidden Web . 52
3.2 Content Richness ... 52
3.3 Web Forum Collection Update Strategies ... 52
3.4 Research Questions ... 53
4 Research Design .... 53
4.1 Proposed Dark Web Forum Crawling System .. 53
4.2 Accessibility . 53
4.3 Incremental Crawling for Collection Updating .... 54
5 System Design ... 54
5.1 Forum Identifi cation .. 54
5.2 Forum Preprocessing ... 56
5.3 Forum Spidering .... 59
5.4 Forum Storage and Analysis .. 60
5.5 Dark Web Forum Crawling System Interface ... 61
Contents xix
6 Evaluation .. 62
6.1 Forum Accessibility Experiment ... 62
6.2 Forum Collection Update Experiment . 63
6.3 Forum Collection Statistics .... 65
7 Conclusions and Future Directions ...... 66
References ..... 67
5 Link and Content Analysis .... 71
1 Introduction ..... 71
2 Literature Review .. 72
2.1 Terrorists’ Use of the Web .. 72
2.2 Information Services for Studying Terrorism ... 73
2.3 Advanced Information Technologies
for Combating Terrorism .... 74
3 A Methodology for Collecting and Analyzing Dark
Web Information ... 75
3.1 The Methodology ... 75
3.2 Discussion of the Methodology ..... 77
4 Jihad on the Web: A Case Study .. 77
4.1 Application of the Methodology .... 78
5 Results and Discussion ... 87
5.1 Expert Evaluation and Results .... 87
6 Conclusions and Future Directions ...... 88
References ..... 89
6 Dark Network Analysis ... 91
1 Introduction ..... 91
2 Topological Analysis of Networks .. 91
3 Methods and Data . 93
4 Results and Discussion ... 94
4.1 Basic Properties ..... 94
4.2 Small-World Properties .... 96
4.3 Scale-Free Properties ... 98
4.4 Caveats ... 99
4.5 Network Robustness . 100
5 Conclusions ..... 102
References ..... 103
7 Interactional Coherence Analysis ... 105
1 Introduction ..... 105
2 Related Work... 107
2.1 Obstacles to CMC Interactional Coherence ... 107
2.2 CMC Interactional Coherence Analysis ..... 108
3 Research Gaps and Questions ... 113
4 System Design: Hybrid Interactional Coherence System .... 114
4.1 Data Preparation ..... 115
4.2 HIC Algorithm: System Feature Match ... 116
xx Contents
4.3 HIC Algorithm: Linguistic Feature Match .... 117
4.4 HIC Algorithm: Residual Match .... 119
5 Evaluation .. 120
5.1 Test Bed .... 120
5.2 Comparison of Techniques .... 121
6 Conclusions ..... 123
References ..... 124
8 Dark Web Attribute System .. 127
1 Introduction ..... 127
2 Literature Review .. 128
2.1 Terrorism and the Internet ... 128
2.2 Existing Dark Web Studies .... 129
2.3 Dark Web Collection Building .... 129
2.4 Dark Web Content Analysis ... 132
3 Proposed Methodology: Dark Web Collection and Analysis ... 133
3.1 Dark Web Collection Building .... 134
3.2 The Dark Web Attribute System (DWAS) .. 136
4 Case Study: Understanding Middle Eastern Terrorist Groups ..... 139
4.1 Building Dark Web Research Test Bed .... 140
4.2 Collection Analysis and Benchmark Comparison ... 142
5 Conclusions and Future Directions ...... 149
References ..... 150
9 Authorship Analysis .. 153
1 Introduction ..... 153
2 Literature Review: Authorship Analysis .... 154
2.1 Writing Style Features . 154
2.2 Analysis Techniques . 155
2.3 Online Messages .... 155
2.4 Multilingual Issues .... 156
3 Arabic Language Characteristics .... 156
3.1 Infl ection ... 156
3.2 Diacritics ... 157
3.3 Word Length and Elongation ...... 157
4 Research Questions and Research Design . 158
4.1 Test Bed .... 158
4.2 Analysis Techniques . 159
4.3 Addressing Arabic Characteristics .... 159
4.4 Feature Sets .. 160
5 Authorship Identifi cation Procedure .... 162
5.1 Collection and Extraction ... 162
5.2 Experiment ... 163
6 Results and Discussion ... 163
6.1 Comparison of Feature Types ..... 164
6.2 Comparison of Classifi cation Techniques ... 164
Contents xxi
7 Analysis of English and Arabic Group Models ... 165
7.1 Decision Tree Analysis .... 165
7.2 Feature Usage Analysis .... 166
8 Conclusions and Future Directions ...... 168
References ..... 169
10 Sentiment Analysis .... 171
1 Introduction ..... 171
2 Related Work... 172
2.1 Sentiment Classifi cation... 172
2.2 Sentiment Analysis Tasks ... 173
2.3 Sentiment Analysis Features .. 175
2.4 Sentiment Classifi cation Techniques ... 176
2.5 Sentiment Analysis Domains ...... 177
3 Research Gaps and Questions ... 178
3.1 Web Forums in Multiple Languages . 178
3.2 Stylistic Features .... 178
3.3 Feature Reduction for Sentiment Classifi cation ... 179
3.4 Research Questions ... 179
4 Research Design .... 179
5 System Design ... 181
5.1 Feature Extraction .. 181
5.2 Feature Selection: Entropy Weighted Genetic
Algorithm (EWGA) .. 184
5.3 Classifi cation ... 188
6 System Evaluation. 188
6.1 Test Bed .... 189
6.2 Experiment 1a: Evaluation of Features .... 190
6.3 Experiment 1b: Evaluation of Feature
Selection Techniques ... 191
6.4 Results Discussion .... 192
7 Conclusions and Future Directions ...... 197
References ..... 197
11 Affect Analysis ..... 203
1 Introduction ..... 203
2 Related Work... 204
2.1 Features for Affect Analysis .. 206
2.2 Techniques for Assigning Affect Intensities .. 208
3 Research Design .... 209
3.1 Gaps and Questions ... 209
3.2 Research Framework . 210
3.3 Research Hypotheses ... 214
4 Evaluation .. 214
4.1 Test Bed .... 214
4.2 Experimental Design . 215
xxii Contents
4.3 Experiment 1: Comparison of Feature Sets ... 216
4.4 Experiment 2: Comparison of Techniques .. 217
4.5 Experiment 3: Ablation Testing ..... 218
4.6 Hypotheses Results ... 218
5 Case Study: Al-Firdaws vs. Montada ..... 220
6 Conclusions ..... 223
References ..... 223
12 CyberGate Visualization .... 227
1 Introduction ..... 227
2 Background ..... 229
2.1 CMC Content .. 229
2.2 CMC Systems ..... 230
2.3 Need for CMC Systems Supporting Text Analysis .... 232
3 CMC Text Mining . 233
3.1 Tasks.. 233
3.2 Information Types .. 234
3.3 Features ..... 235
3.4 Feature Selection .... 236
3.5 Visualization ... 237
4 A Design Framework for CMC Text Analysis .... 238
4.1 Meta-requirements .... 240
4.2 Meta-design .. 240
5 System Design: The CyberGate System .... 241
5.1 Information Types and Features ..... 241
5.2 Feature Selection .... 242
5.3 Visualization ... 243
5.4 Writeprints and Ink Blots .... 245
6 CyberGate Case Studies: Clearguidance.com
and Ummah.com ... 248
6.1 Clearguidance.com .... 248
6.2 Ummah.com . 250
7 Conclusions ..... 252
References ..... 253
13 Dark Web Forum Portal .... 257
1 Introduction ..... 257
2 Literature Review .. 258
2.1 Incremental Forum Spidering ..... 258
2.2 Multilingual Translation ..... 259
2.3 Social Network Analysis on Web Forums .. 259
3 Motivation and Research Questions..... 260
4 System Design ... 261
4.1 Data Acquisition .... 261
4.2 Data Preparation ..... 263
4.3 System Functionality ... 263
Contents xxiii
5 Data Set: Dark Web Forums . 263
6 System Functionality ... 264
6.1 Forum Browsing and Searching ..... 265
6.2 Social Network Visualization ..... 266
7 Case Study: Identifying Active Participants in Dark Web
Forums Using Social Network Analysis .... 268
8 Conclusions and Future Directions ...... 269
References ..... 269
Part III Dark Web Research: Case Studies
14 Jihadi Video Analysis ... 273
1 Introduction ..... 273
2 Jihadi Groups’ Videos ..... 274
2.1 Dissemination of Extremist Groups’ Videos . 275
3 Collections of Extremist Groups’ Videos .. 276
4 Content Analysis of Videos .. 278
4.1 Sample Collection .. 279
4.2 Coding the Videos .. 279
4.3 Inter-coder Reliability .. 280
5 Types of Videos Produced .. 280
5.1 Documentary Videos . 280
5.2 Suicide Attack Videos .. 282
6 How the Groups Used the Videos ... 283
6.1 Groups Identifi ed ... 284
7 Groups’ Modus Operandi and Production Features ... 285
7.1 Production Features .. 286
8 Conclusions ..... 287
Appendix A List of Sample Videos ... 289
Appendix B Coding Scheme . 291
References ..... 292
15 Extremist YouTube Videos .... 295
1 Introduction ..... 295
2 Literature Review .. 296
2.1 Video Domains .... 298
2.2 Feature Types .. 299
2.3 Classifi cation Techniques .... 301
3 Research Gaps and Research Questions .... 302
4 System Design ... 304
4.1 Data Collection ... 304
4.2 Feature Generation .... 305
4.3 Classifi cation and Evaluation ...... 308
5 Test Bed and Hypotheses ... 309
5.1 Test Bed .... 309
5.2 Hypotheses ... 310
xxiv Contents
6 Experiment Results and Discussion ..... 311
7 A Case Study: Domestic Extremist Videos .. 311
8 Conclusions and Future Directions ...... 313
References ..... 314
16 Improvised Explosive Devices (IED) on Dark Web . 319
1 Introduction ..... 319
2 Cyber-Archaeology Framework for Social
Movement Research ..... 321
3 Case Study ...... 323
3.1 Introduction .. 323
3.2 Cyber-Archaeology Framework Phase 1 .... 324
3.3 Cyber-Archaeology Framework Phase 2 .... 325
3.4 Cyber-Archaeology Framework Phase 3 .... 332
4 Conclusion ...... 337
References ..... 338
17 Weapons of Mass Destruction (WMD) on Dark Web . 341
1 Introduction ..... 341
2 Literature Review: Knowledge Mapping and Focused
Web Crawling .... 342
2.1 Knowledge Mapping . 342
2.2 Focused Web Crawling .... 343
3 The Capability-Accessibility-Intent Model for Nuclear
Threat Detection: Nuclear Web and Dark Web .... 344
3.1 Capability .. 345
3.2 Accessibility . 345
3.3 Intent ...... 346
4 Case Study: Nuclear Web and Dark Web .. 346
4.1 Knowledge Mapping for Nuclear Web .... 346
4.2 Focused Web Crawling for Dark Web . 347
5 Conclusions ..... 352
References ..... 353
18 Bioterrorism Knowledge Mapping .... 355
1 Introduction ..... 355
2 Literature Review .. 356
2.1 Bioterrorism Literature Analysis ... 356
2.2 Knowledge Mapping . 356
3 Research Test Bed . 358
4 Research Design .... 359
4.1 Data Acquisition .... 360
4.2 Data Parsing and Cleaning .. 360
4.3 Data Analysis .. 361
Contents xxv
5 Analysis Results and Discussion .... 361
5.1 Productivity Status of Bioterrorism Research ... 361
5.2 Collaboration Status of Bioterrorism Researchers ... 362
5.3 Emerging Topics of Bioterrorism Research ... 364
6 Conclusions and Future Directions ...... 366
References ..... 366
19 Women’s Forums on the Dark Web .. 369
1 Introduction ..... 369
2 Literature Review .. 370
2.1 Online Gender Differences .... 370
2.2 Online Text Classifi cation ... 372
3 Research Gaps and Questions ... 376
4 Research Design .... 377
4.1 Web Forum Message Acquisition .. 377
4.2 Feature Generation .... 377
4.3 Classifi cation and Evaluation ...... 380
5 Experimental Study .. 381
5.1 Test Bed .... 381
5.2 Hypotheses ... 382
5.3 Experimental Results ... 382
5.4 Different Topics of Interest: Females and Males ..... 382
6 Conclusions and Future Directions ...... 385
References ..... 386
20 US Domestic Extremist Groups ... 391
1 Introduction ..... 391
2 Previous Research . 392
2.1 Social Movement Research on Extremists
and the Internet ... 392
2.2 Web Harvesting Approaches .. 393
2.3 Web Link and Content Analysis .... 394
3 Proposed Approach .. 395
3.1 Collection Building ... 395
3.2 Link Analysis .. 397
3.3 Content Analysis .... 398
4 Test Bed: Collection of Domestic Extremist Web Sites ... 399
5 Analysis Results .... 400
5.1 Link Analysis Results .. 400
5.2 Content Analysis Results .... 402
6 Conclusions and Future Work ... 404
References ..... 404
xxvi Contents
21 International **** Gong Movement on the Web ... 407
1 Introduction ..... 407
2 Literature Review .. 408
2.1 Social Movement Theory .... 408
2.2 Social Movement Organizations and the Internet .... 409
2.3 Social Network Analysis ..... 410
2.4 Writeprints ... 411
3 Research Design: A Case Study of the International
FLG Movement .. 412
3.1 The **** Gong Movement ... 412
3.2 Research Design ..... 413
4 Research Results ... 417
4.1 Link Analysis .. 417
4.2 Web Content Analysis .. 419
4.3 Forum Content Analysis ..... 419
5 Conclusions ..... 423
References ..... 424
22 Botnets and Cyber Criminals .. 427
1 Introduction ..... 427
1.1 The Underground Economy ... 429
1.2 Terrorism Online .... 430
2 Research Test Bed: The Shadowserver Foundation ... 431
2.1 Honeypots .... 431
2.2 Malware Analysis .. 431
2.3 Snooping ... 432
3 Investigating the Botnet World .... 432
3.1 Dataset Processing .... 433
3.2 Criminal Social Networks ... 435
4 Future Work .... 438
5 Conclusions ..... 438
References ..... 439
Index ..... 441