Machine Learning for Authorship Attribution and Cyber Forensics

 
 
Springer (Verlag)
  • erschienen am 5. Dezember 2021
 
  • Buch
  • |
  • Softcover
  • |
  • IX, 158 Seiten
978-3-030-61677-9 (ISBN)
 

The book first explores the cybersecurity's landscape and the inherent susceptibility of online communication system such as e-mail, chat conversation and social media in cybercrimes. Common sources and resources of digital crimes, their causes and effects together with the emerging threats for society are illustrated in this book. This book not only explores the growing needs of cybersecurity and digital forensics but also investigates relevant technologies and methods to meet the said needs. Knowledge discovery, machine learning and data analytics are explored for collecting cyber-intelligence and forensics evidence on cybercrimes.

Online communication documents, which are the main source of cybercrimes are investigated from two perspectives: the crime and the criminal. AI and machine learning methods are applied to detect illegal and criminal activities such as bot distribution, drug trafficking and child pornography. Authorship analysis is applied to identify the potential suspects and their social linguistics characteristics. Deep learning together with frequent pattern mining and link mining techniques are applied to trace the potential collaborators of the identified criminals.

Finally, the aim of the book is not only to investigate the crimes and identify the potential suspects but, as well, to collect solid and precise forensics evidence to prosecute the suspects in the court of law.


1st ed. 2020
  • Englisch
  • Cham
  • |
  • Schweiz
Springer International Publishing
  • Für Beruf und Forschung
  • 28
  • |
  • 10 s/w Abbildungen, 28 farbige Abbildungen
  • |
  • 28 Illustrations, color; 10 Illustrations, black and white; IX, 158 p. 38 illus., 28 illus. in color.
  • Höhe: 23.5 cm
  • |
  • Breite: 15.5 cm
  • 267 gr
978-3-030-61677-9 (9783030616779)
10.1007/978-3-030-61675-5
weitere Ausgaben werden ermittelt

1 CYBERSECURITY AND CYBERCRIME INVESTIGATION 1.1 CYBERSECURITY 1.2 KEY COMPONENTS TO MINIMIZING CYBERCRIMES 1.3 DAMAGE RESULTING FROM CYBERCRIME 1.4 CYBERCRIMES 1.4.1 Major Categories of Cybercrime 1.4.2 Causes of and Motivations for Cybercrime 1.5 MAJOR CHALLENGES 1.5.1 Hacker Tools and Exploit Kits 1.5.2 Universal Access 291.5.3 Online Anonymity 1.5.4 Organized Crime 301.5.5 Nation State Threat Actors 311.6 CYBERCRIME INVESTIGATION 322 MACHINE LEARNING FRAMEWORK FOR MESSAGING FORENSICS 342.1 SOURCES OF CYBERCRIMES 362.2 FEW ANALYSIS TOOLS AND TECHNIQUES 382.3 PROPOSED FRAMEWORK FOR CYBERCRIMES INVESTIGATION 392.4 AUTHORSHIP ANALYSIS 412.5 INTRODUCTION TO CRIMINAL INFORMATION MINING 432.5.1 Existing Criminal Information Mining Approaches 442.5.2 WordNet-based Criminal Information Mining 472.6 WEKA 483 HEADER-LEVEL INVESTIGATION AND ANALYZING NETWORK INFORMATION 503.1 STATISTICAL EVALUATION 523.2 TEMPORAL ANALYSIS 533.3 GEOGRAPHICAL LOCALIZATION 533.4 SOCIAL NETWORK ANALYSIS 553.5 CLASSIFICATION 563.6 CLUSTERING 584 AUTHORSHIP ANALYSIS APPROACHES 594.1 HISTORICAL PERSPECTIVE 594.2 ONLINE ANONYMITY AND AUTHORSHIP ANALYSIS 604.3 STYLOMETRIC FEATURES 614.4 AUTHORSHIP ANALYSIS METHODS 634.4.1 Statistical Analysis Methods 644.4.2 Machine Learning Methods 644.4.1 Classification Method Fundamentals 664.5 AUTHORSHIP ATTRIBUTION 674.6 AUTHORSHIP CHARACTERIZATION 694.7 AUTHORSHIP VERIFICATION 704.8 LIMITATIONS OF EXISTING AUTHORSHIP TECHNIQUES 725 AUTHORSHIP ANALYSIS - WRITEPRINT MINING FOR AUTHORSHIP ATTRIBUTION 745.1 AUTHORSHIP ATTRIBUTION PROBLEM 785.1.1 Attribution without Stylistic Variation 795.1.2 Attribution with Stylistic Variation 795.2 BUILDING BLOCKS OF THE PROPOSED APPROACH 805.3 WRITEPRINT 875.4 PROPOSED APPROACHES 875.4.1 AuthorMiner1: Attribution without Stylistic Variation 885.4.2 AuthorMiner2: Attribution with Stylistic Variation 926 AUTHORSHIP ATTRIBUTION WITH FEW TRAINING SAMPLES 976.1 PROBLEM STATEMENT AND FUNDAMENTALS 1006.2 PROPOSED APPROACH 1016.2.1 Preprocessing 1016.2.2 Clustering by Stylometric Features 1026.2.3 Frequent Stylometric Pattern Mining 1046.2.4 Writeprint Mining 1056.2.5 Identifying Author 1066.3 EXPERIMENTS AND DISCUSSION 1067 AUTHORSHIP CHARACTERIZATION 1137.1 PROPOSED APPROACH 1157.1.1 Clustering Anonymous Messages 1167.1.2 Extracting Writeprints from Sample Messages 1167.1.3 Identifying Author Characteristics 1167.2 EXPERIMENTS AND DISCUSSION 1178 AUTHORSHIP VERIFICATION 1208.1 PROBLEM STATEMENT 1238.2 PROPOSED APPROACH 1258.2.1 Verification by Classification 1268.2.2 Verification by Regression 1268.3 EXPERIMENTS AND DISCUSSION 1278.3.1 Verification by Classification. 1288.3.2 Verification by Regression 1289 AUTHORSHIP ATTRIBUTION USING CUSTOMIZED ASSOCIATIVE CLASSIFICATION 1319.1 PROBLEM STATEMENT 1329.1.1 Extracting Stylometric Features 1329.1.2 Associative Classification Writeprint 1339.1.3 Refined Problem Statement 1369.2 CLASSIFICATION BY MULTIPLE ASSOCIATION RULE FOR AUTHORSHIP ANALYSIS 1379.2.1 Mining Class Association Rules 1379.2.2 Pruning Class Association Rules 1399.2.3 Authorship Classification 1429.3 EXPERIMENTAL EVALUATION 14510 CRIMINAL INFORMATION MINING 15110.1 PROBLEM STATEMENT 15310.1.1 Subproblem: Clique Mining 15410.1.2 Subproblem: Concept Analysis 15610.2 PROPOSED APPROACH 15610.2.1 Clique Miner 15710.2.2 Concept Miner 16010.2.3 Information Visualizer 16510.3 EXPERIMENTS AND DISCUSSION 16611 ARTIFICIAL INTELLIGENCE AND DIGITAL FORENSICS 17211.1 AI TECHNIQUES 17311.2 DEEP LEARNING FOR SOCIAL MEDIA MINING 17611.2.1 Tweet Crawler 17811.2.2 Preprocessing 17811.2.3 Event Identifier 17811.2.4 Event Filter 18011.2.5 Information Extractor 18011.3 FUTURE APPLICATION AND IMPLICATIONS FOR DIGITAL FORENSICS 183
DNB DDC Sachgruppen

Versand in 7-9 Tagen

106,99 €
inkl. 7% MwSt.
In den Warenkorb