{"product_id":"artificial-intelligence-ai-in-forensic-sciences-isbn-9781119813323","title":"Artificial Intelligence (AI) in Forensic Sciences","description":"\u003cp\u003e\u003cb\u003eARTIFICIAL INTELLIGENCE (AI) IN FORENSIC SCIENCES\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003cb\u003eFoundational text for teaching and learning within the field of Artificial Intelligence (AI) as it applies to forensic science\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003ci\u003eArtificial Intelligence (AI) in Forensic Sciences\u003c\/i\u003e presents an overview of the state-of-the-art applications of Artificial Intelligence within Forensic Science, covering issues with validation and new crimes that use AI; issues with triage, preselection, identification, argumentation and explain ability; demonstrating uses of AI in forensic science; and providing discussions on bias when using AI. \u003c\/p\u003e\u003cp\u003eThe text discusses the challenges for the legal presentation of AI data and interpretation and offers solutions to this problem while addressing broader practical and emerging issues in a growing area of interest in forensics. It builds on key developing areas of focus in academic and government research, providing an authoritative and well-researched perspective. \u003c\/p\u003e\u003cp\u003eCompiled by two highly qualified editors with significant experience in the field, and part of the Wiley — AAFS series ‘Forensic Science in Focus’, \u003ci\u003eArtificial Intelligence (AI) in Forensic Sciences\u003c\/i\u003e includes information on: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003eCyber IoT, fundamentals on AI in forensic science, speaker and facial comparison, and deepfake detection\u003c\/li\u003e \u003cli\u003eDigital-based evidence creation, 3D and AI, interoperability of standards, and forensic audio and speech analysis\u003c\/li\u003e \u003cli\u003eText analysis, video and multimedia analytics, reliability, privacy, network forensics, intelligence operations, argumentation support in court, and case applications\u003c\/li\u003e \u003cli\u003eIdentification of genetic markers, current state and federal legislation with regards to AI, and forensics and fingerprint analysis\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003eProviding comprehensive coverage of the subject, \u003ci\u003eArtificial Intelligence (AI) in Forensic Sciences\u003c\/i\u003e is an essential advanced text for final year undergraduates and master’s students in forensic science, as well as universities teaching forensics (police, IT security, digital science and engineering), forensic product vendors and governmental and cyber security agencies. \u003c\/p\u003e\u003cp\u003eAbout the editors, ix\u003c\/p\u003e \u003cp\u003eList of Contributors, x\u003c\/p\u003e \u003cp\u003eSeries Preface, xi\u003c\/p\u003e \u003cp\u003ePreface Book, xii\u003c\/p\u003e \u003cp\u003eAcknowledgements, xiii\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Introduction, 1\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eZeno Geradts and Katrin Franke\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 AI-based Forensic Evaluation in Court: The Desirability of Explanation and the Necessity of Validation, 3\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eRolf J.F. Ypma, Daniel Ramos, and Didier Meuwly\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e2.1 Introduction, 3\u003c\/p\u003e \u003cp\u003e2.1.1 AI for Forensic Evaluation, 6\u003c\/p\u003e \u003cp\u003e2.2 The Desirability for Explanation and the Necessity of Validation, 7\u003c\/p\u003e \u003cp\u003e2.3 Explainability (and its Validity), 8\u003c\/p\u003e \u003cp\u003e2.3.1 Reasons to Pursue Explanations, 9\u003c\/p\u003e \u003cp\u003e2.3.2 Types of Explanations, 9\u003c\/p\u003e \u003cp\u003e2.3.3 Limitations of Explanations, 11\u003c\/p\u003e \u003cp\u003e2.4 Validation (and its Explanation), 11\u003c\/p\u003e \u003cp\u003e2.4.1 Measure the Method's Performance, 12\u003c\/p\u003e \u003cp\u003e2.4.2 Approach in Four Steps, 12\u003c\/p\u003e \u003cp\u003e2.4.3 Accountability, 16\u003c\/p\u003e \u003cp\u003e2.5 Conclusion, 17\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Machine Learning for Evidence in Criminal Proceedings: Techno-legal Challenges for Reliability Assurance, 21\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eRadina Stoykova, Jeanne Mifsud Bonnici, and Katrin Franke\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e3.1 Introduction: AI in the Intersection of Criminal Procedure and Forensics, 21\u003c\/p\u003e \u003cp\u003e3.1.1 Technical Fragmentation in Digital Investigations, 21\u003c\/p\u003e \u003cp\u003e3.1.2 Legal and Methodological Fragmentation in Digital Investigations, 22\u003c\/p\u003e \u003cp\u003e3.1.3 Specifics of ML-based Investigative Approach, 23\u003c\/p\u003e \u003cp\u003e3.1.4 Scope and Definitions, 25\u003c\/p\u003e \u003cp\u003e3.2 Legal Framework, 27\u003c\/p\u003e \u003cp\u003e3.2.1 The Fair Trial Principle, 28\u003c\/p\u003e \u003cp\u003e3.2.2 Necessity and Proportionality of Investigative Measures, 32\u003c\/p\u003e \u003cp\u003e3.2.3 The AIA Proposal, 33\u003c\/p\u003e \u003cp\u003e3.2.4 AI System Development and Legislative Contradictions, 35\u003c\/p\u003e \u003cp\u003e3.3 Machine Learning Pipelines: Techno-legal Challenges, 44\u003c\/p\u003e \u003cp\u003e3.3.1 Task + Purpose Limitation and Data Minimization, 44\u003c\/p\u003e \u003cp\u003e3.3.2 Dataset Engineering and Data Governance, 48\u003c\/p\u003e \u003cp\u003e3.3.3 Pre-processing for Input: Trade-offs between Accuracy and Computational Costs, 53\u003c\/p\u003e \u003cp\u003e3.3.4 Modelling, 56\u003c\/p\u003e \u003cp\u003e3.4 AI Use in Investigations: AI System Design + Data Protection = Fair Trial?, 63\u003c\/p\u003e \u003cp\u003e3.5 Conclusion, 66\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Formalising Representation and Interpretation of Digital Evidence to Reinforce Reasoning and Automated Analysis, 74\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eEoghan Casey and Timothy Bollé\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction, 74\u003c\/p\u003e \u003cp\u003e4.2 Background and Related Work, 76\u003c\/p\u003e \u003cp\u003e4.3 Method, 77\u003c\/p\u003e \u003cp\u003e4.4 Representing Digital Traces, 79\u003c\/p\u003e \u003cp\u003e4.5 Representing Computed Similarity, 86\u003c\/p\u003e \u003cp\u003e4.6 Representing ML Classification, 89\u003c\/p\u003e \u003cp\u003e4.7 Representing Hypothesis Test Results (a.k.a. Inferences), 91\u003c\/p\u003e \u003cp\u003e4.7.1 Location Example, 93\u003c\/p\u003e \u003cp\u003e4.7.2 Identification Example, 95\u003c\/p\u003e \u003cp\u003e4.8 Effective\/Reliable\/Responsible Automated Analysis, 99\u003c\/p\u003e \u003cp\u003e4.9 Conclusion, 101\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Servicing Digital Investigations with Artificial Intelligence, 103\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eHarm van Beek and Hans Henseler\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction, 103\u003c\/p\u003e \u003cp\u003e5.2 Introduction To Hansken, 104\u003c\/p\u003e \u003cp\u003e5.2.1 Normalized Trace Model, 105\u003c\/p\u003e \u003cp\u003e5.2.2 Forensic Tool Application, 106\u003c\/p\u003e \u003cp\u003e5.2.3 Hansken's Application Programming Interfaces, 108\u003c\/p\u003e \u003cp\u003e5.3 Large Scale Application of AI Techniques, 109\u003c\/p\u003e \u003cp\u003e5.3.1 Rule-based AI Techniques Implemented in Hansken, 109\u003c\/p\u003e \u003cp\u003e5.3.2 Deep-learning AI Techniques Currently Implemented in Hansken, 111\u003c\/p\u003e \u003cp\u003e5.3.3 Deep-learning AI Techniques to be Implemented in Hansken, 115\u003c\/p\u003e \u003cp\u003e5.3.4 The application of large language models in digital forensics, 118\u003c\/p\u003e \u003cp\u003e5.4 Conclusions and Further Reading, 120\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 On the Feasibility of Social Network Analysis Methods for Investigating Large-scale Criminal Networks, 123\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eJan William Johnsen and Katrin Franke\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction, 123\u003c\/p\u003e \u003cp\u003e6.2 Previous Work, 125\u003c\/p\u003e \u003cp\u003e6.3 Material and Methods, 127\u003c\/p\u003e \u003cp\u003e6.3.1 Real-world Underground Forum Database Dumps, 127\u003c\/p\u003e \u003cp\u003e6.3.2 Network Centrality Measures, 129\u003c\/p\u003e \u003cp\u003e6.3.3 Measuring Association Using Bi-variate Analysis, 129\u003c\/p\u003e \u003cp\u003e6.3.4 Topic Modelling Algorithms, 130\u003c\/p\u003e \u003cp\u003e6.4 Experimental Setup, 130\u003c\/p\u003e \u003cp\u003e6.4.1 Evaluating Network Centrality Measures for Forensics, 130\u003c\/p\u003e \u003cp\u003e6.4.2 Our Novel Approach for Analysing Cybercriminal's Technical Skills, 133\u003c\/p\u003e \u003cp\u003e6.5 Experimental Results and Discussion, 137\u003c\/p\u003e \u003cp\u003e6.5.1 Correlation Testing, 137\u003c\/p\u003e \u003cp\u003e6.5.2 Our Newly Proposed Method, 142\u003c\/p\u003e \u003cp\u003e6.6 Conclusion, 145\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Mapping NLP Techniques to Investigations and Investigative Interviews, 149\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eKyle Porter and Bente Skattør\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e7.1 Introduction, 149\u003c\/p\u003e \u003cp\u003e7.2 Criminal Investigation, 150\u003c\/p\u003e \u003cp\u003e7.2.1 Investigative Interviews, 150\u003c\/p\u003e \u003cp\u003e7.3 Assessing the Needs of Investigators in an NLP Context, 151\u003c\/p\u003e \u003cp\u003e7.3.1 Mapping Interviewer Needs to Existing NLP Tasks, 151\u003c\/p\u003e \u003cp\u003e7.4 Automatic Speech Recognition, 152\u003c\/p\u003e \u003cp\u003e7.4.1 ASR Basics, 152\u003c\/p\u003e \u003cp\u003e7.4.2 ASR, Digital Investigation, and the State of the Art, 153\u003c\/p\u003e \u003cp\u003e7.5 NLP Basics, 154\u003c\/p\u003e \u003cp\u003e7.5.1 Common Terminology, 154\u003c\/p\u003e \u003cp\u003e7.5.2 Vector Space Models and Embeddings, 156\u003c\/p\u003e \u003cp\u003e7.5.3 Modern NLP Models, 157\u003c\/p\u003e \u003cp\u003e7.6 Text Extraction, 157\u003c\/p\u003e \u003cp\u003e7.6.1 Entity Identification and Named Entity Recognition, 157\u003c\/p\u003e \u003cp\u003e7.6.2 Named Entity Recognition Metrics, 158\u003c\/p\u003e \u003cp\u003e7.6.3 NER Applied to Investigations, 159\u003c\/p\u003e \u003cp\u003e7.6.4 Entity Linking, 159\u003c\/p\u003e \u003cp\u003e7.6.5 Limitations of Using NER, 160\u003c\/p\u003e \u003cp\u003e7.6.6 Extraction Methods outside NER, 161\u003c\/p\u003e \u003cp\u003e7.7 Text Classification, 161\u003c\/p\u003e \u003cp\u003e7.7.1 Classification Evaluation Metrics, 162\u003c\/p\u003e \u003cp\u003e7.7.2 Text Classification and Digital Investigation, 162\u003c\/p\u003e \u003cp\u003e7.7.3 Classification Limitations, 163\u003c\/p\u003e \u003cp\u003e7.8 Text Reduction, 164\u003c\/p\u003e \u003cp\u003e7.8.1 Thematic Extraction and Topic Modelling, 164\u003c\/p\u003e \u003cp\u003e7.8.2 Topic Modelling and Digital Investigations, 165\u003c\/p\u003e \u003cp\u003e7.8.3 Limitations of Topic Modelling, 166\u003c\/p\u003e \u003cp\u003e7.8.4 Text Summarization, 166\u003c\/p\u003e \u003cp\u003e7.8.5 Text Summarization and Digital Investigations, 167\u003c\/p\u003e \u003cp\u003e7.8.6 Summarization Limitations, 167\u003c\/p\u003e \u003cp\u003e7.9 Discussion and Conclusion, 167\u003c\/p\u003e \u003cp\u003e7.9.1 Future Work, 169\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 The Influence of Compression on the Detection of Deepfake Videos, 174\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eMeike Kombrink and Zeno Geradts\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction, 174\u003c\/p\u003e \u003cp\u003e8.2 Method, 178\u003c\/p\u003e \u003cp\u003e8.2.1 Dataset, 178\u003c\/p\u003e \u003cp\u003e8.2.2 Deepfake Detection, 180\u003c\/p\u003e \u003cp\u003e8.3 Results, 183\u003c\/p\u003e \u003cp\u003e8.3.1 Compressed Dataset, 183\u003c\/p\u003e \u003cp\u003e8.3.2 Algorithms, 184\u003c\/p\u003e \u003cp\u003e8.4 Discussion, 190\u003c\/p\u003e \u003cp\u003e8.4.1 Deepfake Detection, 190\u003c\/p\u003e \u003cp\u003e8.4.2 Compression, 191\u003c\/p\u003e \u003cp\u003e8.4.3 Future Work, 193\u003c\/p\u003e \u003cp\u003e8.5 Conclusion, 193\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Event Log Analysis and Correlation: A Digital Forensic Perspective, 195\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eNeminath Hubballi and Pratibha Khandait\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction, 195\u003c\/p\u003e \u003cp\u003e9.2 Sources of Logs, 197\u003c\/p\u003e \u003cp\u003e9.2.1 End Host System Logs, 198\u003c\/p\u003e \u003cp\u003e9.2.2 Networking Devices and Security Applications, 203\u003c\/p\u003e \u003cp\u003e9.2.3 Application Logs, 207\u003c\/p\u003e \u003cp\u003e9.3 Need for Correlation, 208\u003c\/p\u003e \u003cp\u003e9.4 Correlation Techniques, 210\u003c\/p\u003e \u003cp\u003e9.5 Conclusions, 214\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 (Hyper-)graph Analysis and its Application in Forensics, 216\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eMarcel Worring\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction, 216\u003c\/p\u003e \u003cp\u003e10.2 Survey of Methods, 218\u003c\/p\u003e \u003cp\u003e10.2.1 Preliminaries, 218\u003c\/p\u003e \u003cp\u003e10.2.2 Tasks, 219\u003c\/p\u003e \u003cp\u003e10.2.3 Graph Neural Networks, 220\u003c\/p\u003e \u003cp\u003e10.3 Explainability and Visualization, 224\u003c\/p\u003e \u003cp\u003e10.4 Conclusion, 227\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Conclusion, 230\u003c\/b\u003e\u003cbr\u003e\u003ci\u003eZeno Geradts and Katrin Franke\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003eIndex, 232\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eEdited by\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003cb\u003eZeno Geradts,\u003c\/b\u003e is a senior forensic scientist at the Forensic Digital Biometrics Traces Department at the Netherlands Forensic Institute, Ministry of Justice and Security, The Hague, The Netherlands. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eKatrin Franke\u003c\/b\u003e is Professor of Computer Science at the Department of Information Security and Communication Technology at NTNU in Gjøvik, Norway. She has over 25 years’ experience in basic and applied research for financial services and law enforcement agencies (LEAs), working closely with banks and LEAs in Europe, North America and Asia.    \u003c\/p\u003e\u003cp\u003e\u003cb\u003eARTIFICIAL INTELLIGENCE (AI) IN FORENSIC SCIENCES\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003cb\u003eFoundational text for teaching and learning within the field of Artificial Intelligence (AI) as it applies to forensic science\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003ci\u003eArtificial Intelligence (AI) in Forensic Sciences\u003c\/i\u003e presents an overview of the state-of-the-art applications of Artificial Intelligence within Forensic Science, covering issues with validation and new crimes that use AI; issues with triage, preselection, identification, argumentation and explain ability; demonstrating uses of AI in forensic science; and providing discussions on bias when using AI. \u003c\/p\u003e\u003cp\u003eThe text discusses the challenges for the legal presentation of AI data and interpretation and offers solutions to this problem while addressing broader practical and emerging issues in a growing area of interest in forensics. It builds on key developing areas of focus in academic and government research, providing an authoritative and well-researched perspective. \u003c\/p\u003e\u003cp\u003eCompiled by two highly qualified editors with significant experience in the field, and part of the Wiley — AAFS series ‘Forensic Science in Focus’, \u003ci\u003eArtificial Intelligence (AI) in Forensic Sciences\u003c\/i\u003e includes information on: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003eCyber IoT, fundamentals on AI in forensic science, speaker and facial comparison, and deepfake detection\u003c\/li\u003e \u003cli\u003eDigital-based evidence creation, 3D and AI, interoperability of standards, and forensic audio and speech analysis\u003c\/li\u003e \u003cli\u003eText analysis, video and multimedia analytics, reliability, privacy, network forensics, intelligence operations, argumentation support in court, and case applications\u003c\/li\u003e \u003cli\u003eIdentification of genetic markers, current state and federal legislation with regards to AI, and forensics and fingerprint analysis\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003eProviding comprehensive coverage of the subject, \u003ci\u003eArtificial Intelligence (AI) in Forensic Sciences\u003c\/i\u003e is an essential advanced text for final year undergraduates and master’s students in forensic science, as well as universities teaching forensics (police, IT security, digital science and engineering), forensic product vendors and governmental and cyber security agencies.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47988764082405,"sku":"NP9781119813323","price":73.5,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119813323.jpg?v=1761781498","url":"https:\/\/k12savings.com\/products\/artificial-intelligence-ai-in-forensic-sciences-isbn-9781119813323","provider":"K12savings","version":"1.0","type":"link"}