Muutke küpsiste eelistusi

E-raamat: Knowledge Discovery for Counterterrorism and Law Enforcement [Taylor & Francis e-raamat]

(Queen's University, Kingston, Ontario, Canada)
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 203,11 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 290,16 €
  • Säästad 30%
Knowledge Discovery for Counterterrorism and Law EnforcementSuurem pilt
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9780429142499

Most of the research aimed at counterterrorism, fraud detection, or other forensic applications assumes that this is a specialized application domain for mainstream knowledge discovery. Unfortunately, knowledge discovery changes completely when the datasets being used have been manipulated in order to conceal some underlying activity. Knowledge Discovery for Counterterrorism and Law Enforcement operates from the premise that detection algorithms must be rethought to be effective in this domain, and presents a new approach based on cutting-edge analysis for use in adversarial settings.



Reveals How Criminals Conceal Information





 



This volume focuses on four main forms of knowledge discovery: prediction, clustering, relationship discovery, and textual analysis. For each of these application areas, the author discusses opportunities for concealment that are available to criminals and reveals some of the tactics that can aid in detecting them. He reviews what is known about the different technologies for each area and evaluates their effectiveness. The book also supplies a preview of technologies currently under development and describes how they will fit in to existing approaches to knowledge discovery.



Provides Proactive Formulas for Staying One Step Ahead of Adversaries





 



While all knowledge-discovery systems are susceptible to manipulation, designers and users of algorithmic systems who are armed with the knowledge of these subversive tactics are better able to create systems to avoid these vulnerabilities. This book delineates an effective process for integrating knowledge-discovery tools, provides a unique understanding of the limits of the technology, and contains a clear presentation of the upsides and pitfalls of data collection. It is a powerful weapon in the arsenal of anyone confronting the increasingly sophistic

Preface xv
List of Figures xix
1 Introduction 1(20)
1.1 What is 'Knowledge Discovery'?
2(4)
1.1.1 Main Forms of Knowledge Discovery
2(2)
1.1.2 The Larger Process
4(2)
1.2 What is an Adversarial Setting?
6(5)
1.3 Algorithmic Knowledge Discovery
11(5)
1.3.1 What is Different about Adversarial Knowledge Discovery?
14(2)
1.4 State of the Art
16(5)
2 Data 21(20)
2.1 Kinds of Data
21(5)
2.1.1 Data about Objects
22(1)
2.1.2 Low-Level Data
22(1)
2.1.3 Data about Connections
23(1)
2.1.4 Textual Data
24(1)
2.1.5 Spatial Data
25(1)
2.2 Data That Changes
26(1)
2.2.1 Slow Changes in the Underlying Situation
26(1)
2.2.2 Change is the Important Property
26(1)
2.2.3 Stream Data
27(1)
2.3 Fusion of Different Kinds of Data
27(3)
2.4 How is Data Collected?
30(3)
2.4.1 Transaction Endpoints
30(1)
2.4.2 Interaction Endpoints
30(1)
2.4.3 Observation Endpoints
31(1)
2.4.4 Human Data Collection
31(1)
2.4.5 Reasons for Data Collection
32(1)
2.5 Can Data Be Trusted?
33(2)
2.5.1 The Problem of Noise
35(1)
2.6 How Much Data?
35(6)
2.6.1 Data Interoperability
37(1)
2.6.2 Domain Knowledge
38(3)
3 High-Level Principles 41(26)
3.1 What to Look for
41(7)
3.2 Subverting Knowledge Discovery
48(5)
3.2.1 Subverting the Data-Collection Phase
48(1)
3.2.2 Subverting the Analysis Phase
49(1)
3.2.3 Subverting the Decision-and-Action Phase
50(1)
3.2.4 The Difficulty of Fabricating Data
50(3)
3.3 Effects of Technology Properties
53(3)
3.4 Sensemaking and Situational Awareness
56(4)
3.4.1 Worldviews
58(2)
3.5 Taking Account of the Adversarial Setting over Time
60(1)
3.6 Does This Book Help Adversaries?
61(1)
3.7 What about Privacy?
62(5)
4 Looking for Risk - Prediction and Anomaly Detection 67(60)
4.1 Goals
67(8)
4.1.1 Misconceptions
67(1)
4.1.2 The Problem of Human Variability
68(1)
4.1.3 The Problem of Computational Difficulty
68(1)
4.1.4 The Problem of Rarity
68(2)
4.1.5 The Problem of Justifiable Preemption
70(1)
4.1.6 The Problem of Hindsight Bias
71(1)
4.1.7 What are the Real Goals?
72(3)
4.2 Outline of Prediction Technology
75(7)
4.2.1 Building Predictors
75(2)
4.2.2 Attributes
77(1)
4.2.3 Missing Values
77(1)
4.2.4 Reasons for a Prediction
78(1)
4.2.5 Prediction Errors
78(2)
4.2.6 Reasons for Errors
80(1)
4.2.7 Ranking
80(2)
4.2.8 Prediction with an Associated Confidence
82(1)
4.3 Concealment Opportunities
82(2)
4.4 Technologies
84(24)
4.4.1 Decision Trees
84(4)
4.4.2 Ensembles of Predictors
88(5)
4.4.3 Random Forests
93(2)
4.4.4 Support Vector Machines
95(6)
4.4.5 Neural Networks
101(2)
4.4.6 Rules
103(2)
4.4.7 Attribute Selection
105(2)
4.4.8 Distributed Prediction
107(1)
4.4.9 Symbiotic Prediction
107(1)
4.5 Tactics and Process
108(5)
4.6 Extending the Process
113(1)
4.7 Special Case: Looking for Matches
114(1)
4.8 Special Case: Looking for Outliers
115(4)
4.9 Special Case: Frequency Ranking
119(4)
4.9.1 Frequent Records
120(1)
4.9.2 Records Seen Before
121(1)
4.9.3 Records Similar to Those Seen Before
122(1)
4.9.4 Records with Some Other Frequency
123(1)
4.10 Special Case: Discrepancy Detection
123(4)
5 Looking for Similarity - Clustering 127(30)
5.1 Goals
128(2)
5.2 Outline of Clustering Technology
130(4)
5.3 Concealment Opportunities
134(1)
5.4 Technologies
135(16)
5.4.1 Distance-Based Clustering
136(2)
5.4.2 Density-Based Clustering
138(1)
5.4.3 Distribution-Based Clustering
139(2)
5.4.4 Decomposition-Based Clustering
141(3)
5.4.5 Hierarchical Clustering
144(2)
5.4.6 Biclustering
146(4)
5.4.7 Clusters and Prediction
150(1)
5.4.8 Symbiotic Clustering
150(1)
5.5 Tactics and Process
151(1)
5.6 Special Case - Looking for Outliers Revisited
152(5)
6 Looking Inside Groups - Relationship Discovery 157(44)
6.1 Goals
158(1)
6.2 Outline of Relationship-Discovery Technology
159(8)
6.2.1 Real-World Graphs
162(3)
6.2.2 Selection in Graphs
165(1)
6.2.3 Analysis of Graphs
166(1)
6.3 Concealment Opportunities
167(3)
6.4 Technologies
170(24)
6.4.1 Social Network Analysis
170(2)
6.4.2 Visualization
172(4)
6.4.3 Pattern Matching/Information Retrieval
176(3)
6.4.4 Single-Node Exploration
179(3)
6.4.5 Unusual-Region Detection
182(1)
6.4.6 Ranking on Graphs
183(2)
6.4.7 Graph Clustering
185(4)
6.4.8 Edge Prediction
189(1)
6.4.9 Anomalous-Substructure Discovery
189(5)
6.4.10 Graphs and Prediction
194(1)
6.5 Tactics and Process
194(7)
7 Discovery from Public Textual Data 201(46)
7.1 Text as it Reveals Internal State
203(1)
7.2 Goals
204(5)
7.2.1 Finding Texts of Interest
205(1)
7.2.2 Finding Content
206(2)
7.2.3 Finding Authors
208(1)
7.2.4 Finding Author Properties
208(1)
7.2.5 Finding Metainformation
208(1)
7.3 Outline of Textual-Analysis Technology
209(5)
7.3.1 Exploring Content
210(3)
7.3.2 Exploring Authorship
213(1)
7.3.3 Exploring Metainformation
213(1)
7.4 Concealment Opportunities
214(2)
7.5 Technologies
216(22)
7.5.1 Collecting Textual Data
216(2)
7.5.2 Extracting Interesting Documents from a Large Set
218(2)
7.5.3 Extracting Named Entities
220(1)
7.5.4 Extracting Concepts
221(2)
7.5.5 Extracting Relationships
223(1)
7.5.6 Extracting Topics
224(2)
7.5.7 Extracting Narrative and Sensemaking
226(1)
7.5.8 Summarization
227(2)
7.5.9 Extracting Intention and Slant
229(1)
7.5.10 Trends in Content
229(1)
7.5.11 Authorship from Large Samples
230(1)
7.5.12 Authorship from Small Samples
231(4)
7.5.13 Detecting Author Properties
235(2)
7.5.14 Extracting Metainformation
237(1)
7.6 Tactics and Process
238(9)
7.6.1 Playing the Adversaries
238(2)
7.6.2 Playing the Audience
240(1)
7.6.3 Fusing Data from Different Contexts
241(6)
8 Discovery in Private Communication 247(26)
8.1 The Impact of Obfuscation
249(1)
8.2 Goals
249(1)
8.3 Concealment Opportunities
249(4)
8.3.1 Encryption
250(1)
8.3.2 Word Substitutions
251(2)
8.4 Technologies
253(16)
8.4.1 Selection of Interesting Communication
253(9)
8.4.2 Content Extraction after Substitution
262(6)
8.4.3 Authorship after Substitution
268(1)
8.4.4 Metainformation after Substitution
268(1)
8.5 Tactics and Process
269(4)
8.5.1 Using a Multifaceted Process for Selection
269(4)
9 Discovering Mental and Emotional State 273(28)
9.1 Frame Analysis for Intentions
274(4)
9.1.1 Goals
275(1)
9.1.2 Frame-Analysis Detection Technology
276(1)
9.1.3 Concealment Opportunities
277(1)
9.1.4 Tactics and Process
277(1)
9.2 Sentiment Analysis
278(3)
9.2.1 Goals
278(1)
9.2.2 Sentiment-Analysis Technology
279(2)
9.2.3 Concealment Opportunities
281(1)
9.3 Mental-State Extraction
281(11)
9.3.1 Goals
282(1)
9.3.2 Mental-State Extraction Technology
283(8)
9.3.3 Concealment Opportunities
291(1)
9.4 Systemic Functional Linguistics
292(9)
9.4.1 Introduction to Systemic Functional Linguistics
293(3)
9.4.2 SFL for Intention Detection
296(1)
9.4.3 SFL for Sentiment Analysis
296(1)
9.4.4 SFL for Mental-State Extraction
297(4)
10 The Bottom Line 301(16)
10.1 Framing the Problem
301(4)
10.2 The Process
305(2)
10.3 Applying the Process
307(4)
10.4 Open Problems
311(6)
10.4.1 Process Improvements
311(1)
10.4.2 Straightforward Technical Problems
312(2)
10.4.3 More-Difficult Technical Advances
314(3)
Bibliography 317
Index 32
Skillicorn, David
Püsilink: https://www.kriso.ee/db/9780429142499_pe.html
Märksõnad: