{"product_id":"ai-for-cybersecurity-research-and-practice-hardback-9781394293742","title":"AI for Cybersecurity; Research and Practice (Hardback) 9781394293742","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eAI for Cybersecurity\u003c\/font\u003e\u003cbr\u003e\r\n\u003cfont size=\"5\"\u003eResearch and Practice\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\u003cp\u003e\u003cfont size=\"4\"\u003eHoubing Herbert Song (Edited by), Song (Author), Elisa Bertino (Edited by), Alvaro Vasquez (Edited by), Huihui Helen Wang (Edited by), Yan Shoshitaishvili (Edited by), Sumit Kumar Jha (Edited by)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9781394293742, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eHardback, published 12 January 2026\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e656 pages\u003cbr\u003e23.1 x 16.3 x 4.3 cm, 1.111 kg\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\r\n\u003cp align=\"justify\"\u003e\u003cstrong\u003e\u003cfont size=\"3\"\u003e\u003cp\u003e\u003cb\u003eInformative reference on the state of the art in cybersecurity and how to achieve a more secure cyberspace\u003c\/b\u003e \u003c\/p\u003e\n\u003cp\u003e\u003ci\u003eAI for Cybersecurity\u003c\/i\u003e presents the state of the art and practice in AI for cybersecurity with a focus on four interrelated defensive capabilities of deter, protect, detect, and respond. The book examines the fundamentals of AI for cybersecurity as a multidisciplinary subject, describes how to design, build, and operate AI technologies and strategies to achieve a more secure cyberspace, and provides why-what-how of each AI technique-cybersecurity task pair to enable researchers and practitioners to make contributions to the field of AI for cybersecurity. \u003c\/p\u003e\n\u003cp\u003eThis book is aligned with the National Science and Technology Council’s (NSTC) 2023 Federal Cybersecurity Research and Development Strategic Plan (RDSP) and President Biden’s Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Learning objectives and 200 illustrations are included throughout the text. \u003c\/p\u003e\n\u003cp\u003eWritten by a team of highly qualified experts in the field, \u003ci\u003eAI for Cybersecurity\u003c\/i\u003e discusses topics including: \u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eRobustness and risks of the methods covered, including adversarial ML threats in model training, deployment, and reuse\u003c\/li\u003e\n\u003cli\u003ePrivacy risks including model inversion, membership inference, attribute inference, re-identification, and deanonymization\u003c\/li\u003e\n\u003cli\u003eForensic and formal methods for analyzing, auditing, and verifying security- and privacy-related aspects of AI components\u003c\/li\u003e\n\u003cli\u003eUse of generative AI systems for improving security and the risks of generative AI systems to security\u003c\/li\u003e\n\u003cli\u003eTransparency and interpretability\/explainability of models and algorithms and associated issues of fairness and bias\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003e\u003ci\u003eAI for Cybersecurity \u003c\/i\u003eis an excellent reference for practitioners in AI for cybersecurity related industries such as commerce, education, energy, financial services, healthcare, manufacturing, and defense. Fourth year undergraduates and postgraduates in computer science and related programs of study will also find it valuable.\u003c\/p\u003e\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003eList of Contributors xix\u003c\/p\u003e \u003cp\u003eForeword xxvii\u003c\/p\u003e \u003cp\u003eAbout the Editors xxxi\u003c\/p\u003e \u003cp\u003ePreface xxxv\u003c\/p\u003e \u003cp\u003eAcknowledgments xxxvii\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 LLMs Are Not Few-shot Threat Hunters 1\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eGlenn A. Fink, Luiz M. Pereira, and Christian W. Stauffer\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e1.1 Overview 1\u003c\/p\u003e \u003cp\u003e1.1.1 AI Is Not Magic 1\u003c\/p\u003e \u003cp\u003e1.1.2 Inherent Difficulty of Human Tasks in Cybersecurity and Threat Hunting 3\u003c\/p\u003e \u003cp\u003e1.2 Large Language Models 4\u003c\/p\u003e \u003cp\u003e1.2.1 Background 4\u003c\/p\u003e \u003cp\u003e1.2.2 Transformers 4\u003c\/p\u003e \u003cp\u003e1.2.3 Pretraining and Fine-tuning 9\u003c\/p\u003e \u003cp\u003e1.2.4 General Limitations 9\u003c\/p\u003e \u003cp\u003e1.3 Threat Hunters 12\u003c\/p\u003e \u003cp\u003e1.3.1 Introduction to Threat Hunting 12\u003c\/p\u003e \u003cp\u003e1.3.2 The Dimensions of Threat Hunting 13\u003c\/p\u003e \u003cp\u003e1.3.3 The Approaches to Threat Hunting 15\u003c\/p\u003e \u003cp\u003e1.3.4 The Process of Threat Hunting 16\u003c\/p\u003e \u003cp\u003e1.3.5 Challenges to Modern Threat Hunting 17\u003c\/p\u003e \u003cp\u003e1.4 Capabilities and Limitations of LLMs in Cybersecurity 18\u003c\/p\u003e \u003cp\u003e1.4.1 General Limitations of LLMs for Cybersecurity 18\u003c\/p\u003e \u003cp\u003e1.4.2 General Capabilities of LLMs Useful for Cybersecurity 20\u003c\/p\u003e \u003cp\u003e1.4.3 Applications of LLMs in Cybersecurity 22\u003c\/p\u003e \u003cp\u003e1.5 Conclusion: Reimagining LLMs as Assistant Threat Hunter 24\u003c\/p\u003e \u003cp\u003eReferences 27\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 LLMs on Support of Privacy and Security of Mobile Apps: State-of-the-art and Research Directions 29\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eTran Thanh Lam Nguyen, Barbara Carminati, and Elena Ferrari\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e2.1 Introduction 29\u003c\/p\u003e \u003cp\u003e2.2 Background on LLMs 32\u003c\/p\u003e \u003cp\u003e2.2.1 Large Language Models 32\u003c\/p\u003e \u003cp\u003e2.2.2 FSL and RAG 39\u003c\/p\u003e \u003cp\u003e2.3 Mobile Apps: Main Security and Privacy Threats 43\u003c\/p\u003e \u003cp\u003e2.4 LLM-based Solutions: State-of-the-art 47\u003c\/p\u003e \u003cp\u003e2.4.1 Vulnerabilities Detection 48\u003c\/p\u003e \u003cp\u003e2.4.2 Bug Detection and Reproduction 50\u003c\/p\u003e \u003cp\u003e2.4.3 Malware Detection 52\u003c\/p\u003e \u003cp\u003e2.5 An LLMs-based Approach for Mitigating Image Metadata Leakage Risks 53\u003c\/p\u003e \u003cp\u003e2.6 Research Challenges 57\u003c\/p\u003e \u003cp\u003e2.7 Conclusion 60\u003c\/p\u003e \u003cp\u003eAcknowledgment 61\u003c\/p\u003e \u003cp\u003eReferences 61\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Machine Learning-based Intrusion Detection Systems: Capabilities, Methodologies, and Open Research Challenges 67\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eChaoyu Zhang, Ning Wang, Y. Thomas Hou, and Wenjing Lou\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e3.1 Introduction 67\u003c\/p\u003e \u003cp\u003e3.2 Basic Concepts and ML for Intrusion Detection 69\u003c\/p\u003e \u003cp\u003e3.2.1 Fundamental Concepts 69\u003c\/p\u003e \u003cp\u003e3.2.2 ml Algorithms for Intrusion Detection 70\u003c\/p\u003e \u003cp\u003e3.2.3 Taxonomy of IDSs 72\u003c\/p\u003e \u003cp\u003e3.2.4 Evaluation Metrics and Datasets 73\u003c\/p\u003e \u003cp\u003e3.3 Capability I: Zero-day Attack Detection with ml 75\u003c\/p\u003e \u003cp\u003e3.3.1 Understanding Zero-day Attacks and Their Impact 75\u003c\/p\u003e \u003cp\u003e3.3.2 General Workflow of ML-IDS for Identifying Zero-day Attacks 75\u003c\/p\u003e \u003cp\u003e3.3.3 Anomaly Detection Mechanisms 76\u003c\/p\u003e \u003cp\u003e3.3.4 Open Research Challenges 77\u003c\/p\u003e \u003cp\u003e3.4 Capability II: Intrusion Explainability Through XAI 79\u003c\/p\u003e \u003cp\u003e3.4.1 Enhancing Transparency and Trust in Intrusion Detection 79\u003c\/p\u003e \u003cp\u003e3.4.2 General Workflow of XAI 80\u003c\/p\u003e \u003cp\u003e3.4.3 XAI Methods for IDS Transparency Enhancement 80\u003c\/p\u003e \u003cp\u003e3.4.4 Open Research Challenges 83\u003c\/p\u003e \u003cp\u003e3.5 Capability III: Intrusion Detection in Encrypted Traffic 84\u003c\/p\u003e \u003cp\u003e3.5.1 Challenges in Intrusion Detection for Encrypted Traffic 84\u003c\/p\u003e \u003cp\u003e3.5.2 Workflow of ML-IDS for Encrypted Traffic 84\u003c\/p\u003e \u003cp\u003e3.5.3 ML-based Solutions for Encrypted Traffic Analysis 84\u003c\/p\u003e \u003cp\u003e3.5.4 Open Research Challenges 87\u003c\/p\u003e \u003cp\u003e3.6 Capability IV: Context-aware Threat Detection and Reasoning with GNNs 88\u003c\/p\u003e \u003cp\u003e3.6.1 Introduction to GNNs in IDS 88\u003c\/p\u003e \u003cp\u003e3.6.2 Workflow of GNNs for Intrusion Detection 88\u003c\/p\u003e \u003cp\u003e3.6.3 Provenance-based Intrusion Detection by GNNs 89\u003c\/p\u003e \u003cp\u003e3.6.4 Open Research Challenges 92\u003c\/p\u003e \u003cp\u003e3.7 Capability V: LLMs for Intrusion Detection and Understanding 93\u003c\/p\u003e \u003cp\u003e3.7.1 The Role of LLMs in Cybersecurity 93\u003c\/p\u003e \u003cp\u003e3.7.2 Leveraging LLMs for Intrusion Detection 94\u003c\/p\u003e \u003cp\u003e3.7.3 A Review of LLM-based IDS 94\u003c\/p\u003e \u003cp\u003e3.7.4 Open Research Challenges 97\u003c\/p\u003e \u003cp\u003e3.8 Summary 97\u003c\/p\u003e \u003cp\u003eReferences 98\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Generative AI for Advanced Cyber Defense 109\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMoqsadur Rahman, Aaron Sanchez, Krish Piryani, Siddhartha Das, Sai Munikoti, Luis de la Torre Quintana, Monowar Hasan, Joseph Aguayo, Monika Akbar, Shahriar Hossain, and Mahantesh Halappanavar\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction 109\u003c\/p\u003e \u003cp\u003e4.2 Motivation and Related Work 111\u003c\/p\u003e \u003cp\u003e4.2.1 AI-supported Vulnerability Management 112\u003c\/p\u003e \u003cp\u003e4.3 Foundations for Cyber Defense 114\u003c\/p\u003e \u003cp\u003e4.3.1 Mapping Vulnerabilities, Weaknesses, and Attack Patterns Using LLMs 115\u003c\/p\u003e \u003cp\u003e4.4 Retrieval-augmented Generation 117\u003c\/p\u003e \u003cp\u003e4.5 KG and Querying 118\u003c\/p\u003e \u003cp\u003e4.5.1 Graph Schema 119\u003c\/p\u003e \u003cp\u003e4.5.2 Neo4j KG Implementation 122\u003c\/p\u003e \u003cp\u003e4.5.3 Cypher Queries 123\u003c\/p\u003e \u003cp\u003e4.6 Evaluation and Results 126\u003c\/p\u003e \u003cp\u003e4.6.1 RAG-based Response Generation 127\u003c\/p\u003e \u003cp\u003e4.6.2 CWE Predictions Using RAG 131\u003c\/p\u003e \u003cp\u003e4.6.3 CWE Predictions Using GPT4-o 136\u003c\/p\u003e \u003cp\u003e4.7 Conclusion 142\u003c\/p\u003e \u003cp\u003eReferences 142\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Enhancing Threat Detection and Response with Generative AI and Blockchain 147\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eDriss El Majdoubi, Souad Sadki, Zakia El Uahhabi, and Mohamed Essaidi\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction 147\u003c\/p\u003e \u003cp\u003e5.2 Cybersecurity Current Issues: Background 148\u003c\/p\u003e \u003cp\u003e5.3 Blockchain Technology for Cybersecurity 150\u003c\/p\u003e \u003cp\u003e5.3.1 Blockchain Benefits for Cybersecurity 150\u003c\/p\u003e \u003cp\u003e5.3.2 Existing Blockchain-based Cybersecurity Solutions 153\u003c\/p\u003e \u003cp\u003e5.4 Combining Generative AI and Blockchain for Cybersecurity 156\u003c\/p\u003e \u003cp\u003e5.4.1 Integration of Generative AI and Blockchain 160\u003c\/p\u003e \u003cp\u003e5.4.2 Understanding Capabilities and Risks 160\u003c\/p\u003e \u003cp\u003e5.4.3 Practical Benefits for Cybersecurity 161\u003c\/p\u003e \u003cp\u003e5.4.4 Limitations and Open Research Issues 161\u003c\/p\u003e \u003cp\u003e5.5 Conclusion 162\u003c\/p\u003e \u003cp\u003eReferences 163\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Privacy-preserving Collaborative Machine Learning 169\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRunhua Xu and James Joshi\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 169\u003c\/p\u003e \u003cp\u003e6.1.1 Objectives and Structure 171\u003c\/p\u003e \u003cp\u003e6.2 Collaborative Learning Overview 172\u003c\/p\u003e \u003cp\u003e6.2.1 Definition and Characteristics 172\u003c\/p\u003e \u003cp\u003e6.2.2 Related Terminologies 174\u003c\/p\u003e \u003cp\u003e6.2.3 Collaborative Decentralized Learning and Collaborative Distributed Learning 175\u003c\/p\u003e \u003cp\u003e6.3 Collaborative Learning Paradigms and Privacy Risks 177\u003c\/p\u003e \u003cp\u003e6.3.1 Key Collaborative Approaches 177\u003c\/p\u003e \u003cp\u003e6.3.2 Privacy Risks in Collaborative Learning 182\u003c\/p\u003e \u003cp\u003e6.3.3 Privacy Inference Attacks in Collaborative Learning 183\u003c\/p\u003e \u003cp\u003e6.4 Privacy-preserving Technologies 187\u003c\/p\u003e \u003cp\u003e6.4.1 The Need for Privacy Preservation 187\u003c\/p\u003e \u003cp\u003e6.4.2 Privacy-preserving Technologies 188\u003c\/p\u003e \u003cp\u003e6.5 Conclusion 195\u003c\/p\u003e \u003cp\u003eReferences 196\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Security and Privacy in Federated Learning 203\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eZhuosheng Zhang and Shucheng Yu\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e7.1 Introduction 203\u003c\/p\u003e \u003cp\u003e7.1.1 Federated Learning 203\u003c\/p\u003e \u003cp\u003e7.1.2 Privacy Threats in FL 205\u003c\/p\u003e \u003cp\u003e7.1.3 Security Issues in FL 207\u003c\/p\u003e \u003cp\u003e7.1.4 Characterize FL 211\u003c\/p\u003e \u003cp\u003e7.2 Privacy-preserving FL 215\u003c\/p\u003e \u003cp\u003e7.2.1 Secure Multiparty Computation 215\u003c\/p\u003e \u003cp\u003e7.2.2 Trust Execution Environments 216\u003c\/p\u003e \u003cp\u003e7.2.3 Secure Aggregation 217\u003c\/p\u003e \u003cp\u003e7.2.4 Differential Privacy 218\u003c\/p\u003e \u003cp\u003e7.3 Enhance Security in FL 219\u003c\/p\u003e \u003cp\u003e7.3.1 Data-poisoning Attack and Nonadaptive Model-poisoning Attack 220\u003c\/p\u003e \u003cp\u003e7.3.2 Model-poisoning Attack 222\u003c\/p\u003e \u003cp\u003e7.4 Secure Privacy-preserving FL 225\u003c\/p\u003e \u003cp\u003e7.4.1 Enhancing Security in FL with DP 225\u003c\/p\u003e \u003cp\u003e7.4.2 Verifiability in Private FL 226\u003c\/p\u003e \u003cp\u003e7.4.3 Security in Private FL 227\u003c\/p\u003e \u003cp\u003e7.5 Conclusion 228\u003c\/p\u003e \u003cp\u003eReferences 229\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Machine Learning Attacks on Signal Characteristics in Wireless Networks 235\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eYan Wang, Cong Shi, Yingying Chen, and Zijie Tang\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction 235\u003c\/p\u003e \u003cp\u003e8.2 Threat Model and Targeted Models 239\u003c\/p\u003e \u003cp\u003e8.2.1 Backdoor Attack Scenarios 239\u003c\/p\u003e \u003cp\u003e8.2.2 Attackers’ Capability 240\u003c\/p\u003e \u003cp\u003e8.2.3 Attackers’ Objective 240\u003c\/p\u003e \u003cp\u003e8.2.4 Targeted ML Models 241\u003c\/p\u003e \u003cp\u003e8.3 Attack Formulation and Challenges 241\u003c\/p\u003e \u003cp\u003e8.3.1 Backdoor Attack Formulation 241\u003c\/p\u003e \u003cp\u003e8.3.2 Challenges 244\u003c\/p\u003e \u003cp\u003e8.4 Poison-label Backdoor Attack 246\u003c\/p\u003e \u003cp\u003e8.4.1 Stealthy Trigger Designs 246\u003c\/p\u003e \u003cp\u003e8.4.2 Backdoor Trigger Optimization 249\u003c\/p\u003e \u003cp\u003e8.5 Clean-label Backdoor Trigger Design 252\u003c\/p\u003e \u003cp\u003e8.5.1 Clean-label Backdoor Trigger Optimization 253\u003c\/p\u003e \u003cp\u003e8.6 Evaluation 255\u003c\/p\u003e \u003cp\u003e8.6.1 Victim ML Model 255\u003c\/p\u003e \u003cp\u003e8.6.2 Experimental Methodology 255\u003c\/p\u003e \u003cp\u003e8.6.3 RF Backdoor Attack Performance 257\u003c\/p\u003e \u003cp\u003e8.6.4 Resistance to Backdoor Defense 259\u003c\/p\u003e \u003cp\u003e8.7 Related Work 261\u003c\/p\u003e \u003cp\u003e8.8 Conclusion 262\u003c\/p\u003e \u003cp\u003eReferences 263\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Secure by Design 267\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMehdi Mirakhorli and Kevin E. Greene\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction 267\u003c\/p\u003e \u003cp\u003e9.1.1 Definitions and Contexts 268\u003c\/p\u003e \u003cp\u003e9.1.2 Core Principles of “Secure by Design” 269\u003c\/p\u003e \u003cp\u003e9.1.3 Principle of Compartmentalization and Isolation 273\u003c\/p\u003e \u003cp\u003e9.2 A Methodological Approach to Secure by Design 275\u003c\/p\u003e \u003cp\u003e9.2.1 Assumption of Breach 275\u003c\/p\u003e \u003cp\u003e9.2.2 Misuse and Abuse Cases to Drive Secure by Design 276\u003c\/p\u003e \u003cp\u003e9.2.3 Secure by Design Through Architectural Tactics 277\u003c\/p\u003e \u003cp\u003e9.2.4 Shifting Software Assurance from Coding Bugs to Design Flaws 282\u003c\/p\u003e \u003cp\u003e9.3 AI in Secure by Design: Opportunities and Challenges 283\u003c\/p\u003e \u003cp\u003e9.4 Conclusion and Future Directions 284\u003c\/p\u003e \u003cp\u003eReferences 284\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 DDoS Detection in IoT Environments: Deep Packet Inspection and Real-world Applications 289\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eNikola Gavric, Guru Bhandari, and Andrii Shalaginov\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction 289\u003c\/p\u003e \u003cp\u003e10.2 DDoS Detection Techniques in Research 294\u003c\/p\u003e \u003cp\u003e10.2.1 Network-based Intrusion Detection Systems 295\u003c\/p\u003e \u003cp\u003e10.2.2 Host-based Intrusion Detection Systems 300\u003c\/p\u003e \u003cp\u003e10.3 Limitations of Research Approaches 303\u003c\/p\u003e \u003cp\u003e10.4 Industry Practices for DDoS Detection 305\u003c\/p\u003e \u003cp\u003e10.5 Challenges in DDoS Detection 309\u003c\/p\u003e \u003cp\u003e10.6 Future Directions 311\u003c\/p\u003e \u003cp\u003e10.7 Conclusion 313\u003c\/p\u003e \u003cp\u003eReferences 314\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Data Science for Cybersecurity: A Case Study Focused on DDoS Attacks 317\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMichele Nogueira, Ligia F. Borges, and Anderson B. Neira\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e11.1 Introduction 317\u003c\/p\u003e \u003cp\u003e11.2 Background 319\u003c\/p\u003e \u003cp\u003e11.2.1 Cybersecurity 320\u003c\/p\u003e \u003cp\u003e11.2.2 Data Science 326\u003c\/p\u003e \u003cp\u003e11.3 State of the Art 333\u003c\/p\u003e \u003cp\u003e11.3.1 Data Acquisition 334\u003c\/p\u003e \u003cp\u003e11.3.2 Data Preparation 335\u003c\/p\u003e \u003cp\u003e11.3.3 Feature Preprocessing 336\u003c\/p\u003e \u003cp\u003e11.3.4 Data Visualization 337\u003c\/p\u003e \u003cp\u003e11.3.5 Data Analysis 338\u003c\/p\u003e \u003cp\u003e11.3.6 ml in Cybersecurity 339\u003c\/p\u003e \u003cp\u003e11.4 Challenges and Opportunities 340\u003c\/p\u003e \u003cp\u003e11.5 Conclusion 341\u003c\/p\u003e \u003cp\u003eAcknowledgments 342\u003c\/p\u003e \u003cp\u003eReferences 342\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 AI Implications for Cybersecurity Education and Future Explorations 347\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eElizabeth Hawthorne, Mihaela Sabin, and Melissa Dark\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e12.1 Introduction 347\u003c\/p\u003e \u003cp\u003e12.2 Postsecondary Cybersecurity Education: Historical Perspective and Current Initiatives 348\u003c\/p\u003e \u003cp\u003e12.2.1 ACM Computing Curricula 348\u003c\/p\u003e \u003cp\u003e12.2.2 National Centers for Academic Excellence in Cybersecurity 356\u003c\/p\u003e \u003cp\u003e12.2.3 ABET Criteria 359\u003c\/p\u003e \u003cp\u003e12.3 Cybersecurity Policy in Secondary Education 361\u003c\/p\u003e \u003cp\u003e12.3.1 US High School Landscape 362\u003c\/p\u003e \u003cp\u003e12.4 Conclusion 367\u003c\/p\u003e \u003cp\u003e12.5 Future Explorations 368\u003c\/p\u003e \u003cp\u003eReferences 368\u003c\/p\u003e \u003cp\u003e\u003cb\u003e13 Ethical AI in Cybersecurity: Quantum-resistant Architectures and Decentralized Optimization Strategies 371\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eAndreou Andreas, Mavromoustakis X. Constandinos, Houbing Song, and Jordi Mongay Batalla\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e13.1 Introduction 371\u003c\/p\u003e \u003cp\u003e13.1.1 Motivation 372\u003c\/p\u003e \u003cp\u003e13.1.2 Contribution 373\u003c\/p\u003e \u003cp\u003e13.1.3 Novelty 373\u003c\/p\u003e \u003cp\u003e13.2 Literature Review 373\u003c\/p\u003e \u003cp\u003e13.3 Overview and Ethical Considerations in AI-centric Cybersecurity 374\u003c\/p\u003e \u003cp\u003e13.4 AML and Privacy Risks in AI Systems 378\u003c\/p\u003e \u003cp\u003e13.5 Forensic and Formal Methods for AI Security 380\u003c\/p\u003e \u003cp\u003e13.5.1 Auditing Tools for Security and Privacy 383\u003c\/p\u003e \u003cp\u003e13.5.2 Transparency, Interpretability, and Trust 383\u003c\/p\u003e \u003cp\u003e13.5.3 Building Secure and Trustworthy AI Systems 384\u003c\/p\u003e \u003cp\u003e13.6 Generative AI and Quantum-resistant Architectures in Cybersecurity 385\u003c\/p\u003e \u003cp\u003e13.6.1 Opportunities and Risks 385\u003c\/p\u003e \u003cp\u003e13.6.2 Threats and Countermeasures 386\u003c\/p\u003e \u003cp\u003e13.6.3 Strategies for Resilience 387\u003c\/p\u003e \u003cp\u003e13.7 Future Directions and Ethical Considerations 387\u003c\/p\u003e \u003cp\u003e13.8 Conclusion 390\u003c\/p\u003e \u003cp\u003eReferences 391\u003c\/p\u003e \u003cp\u003e\u003cb\u003e14 Security Threats and Defenses in AI-enabled Object Tracking Systems 397\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMengjie Jia, Yanyan Li, and Jiawei Yuan\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e14.1 Introduction 397\u003c\/p\u003e \u003cp\u003e14.2 Related Works 398\u003c\/p\u003e \u003cp\u003e14.2.1 UAV Object Tracking 398\u003c\/p\u003e \u003cp\u003e14.2.2 Adversarial Tracking Attacks 399\u003c\/p\u003e \u003cp\u003e14.2.3 Robustness Enhancement Against Attacks 400\u003c\/p\u003e \u003cp\u003e14.3 Methods 401\u003c\/p\u003e \u003cp\u003e14.3.1 Model Architecture 403\u003c\/p\u003e \u003cp\u003e14.3.2 Decision Loss 403\u003c\/p\u003e \u003cp\u003e14.3.3 Feature Loss 404\u003c\/p\u003e \u003cp\u003e14.3.4 l 2 Norm loss 405\u003c\/p\u003e \u003cp\u003e14.4 Evaluation 405\u003c\/p\u003e \u003cp\u003e14.4.1 Experiment Setup 405\u003c\/p\u003e \u003cp\u003e14.4.2 Evaluation Metrics 405\u003c\/p\u003e \u003cp\u003e14.4.3 Results 406\u003c\/p\u003e \u003cp\u003e14.4.4 Tracking Examples 409\u003c\/p\u003e \u003cp\u003e14.5 Conclusion 413\u003c\/p\u003e \u003cp\u003eAcknowledgment 413\u003c\/p\u003e \u003cp\u003eReferences 413\u003c\/p\u003e \u003cp\u003e\u003cb\u003e15 AI for Android Malware Detection and Classification 419\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eSafayat Bin Hakim, Muhammad Adil, Kamal Acharya, and Houbing Herbert Song\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e15.1 Introduction 419\u003c\/p\u003e \u003cp\u003e15.1.1 Security Threats in Android Applications 420\u003c\/p\u003e \u003cp\u003e15.1.2 Challenges in Android Malware Detection 422\u003c\/p\u003e \u003cp\u003e15.1.3 Current Approaches and Limitations 423\u003c\/p\u003e \u003cp\u003e15.2 Design of the Proposed Framework 424\u003c\/p\u003e \u003cp\u003e15.2.1 Core Components and Architecture 424\u003c\/p\u003e \u003cp\u003e15.2.2 Feature Extraction with Attention Mechanism 425\u003c\/p\u003e \u003cp\u003e15.2.3 Feature Extraction with Attention Mechanism 425\u003c\/p\u003e \u003cp\u003e15.2.4 Dimensionality Reduction and Optimization 427\u003c\/p\u003e \u003cp\u003e15.2.5 Classification Using SVMs 427\u003c\/p\u003e \u003cp\u003e15.3 Implementation and Dataset Overview 428\u003c\/p\u003e \u003cp\u003e15.3.1 Dataset Insights 428\u003c\/p\u003e \u003cp\u003e15.3.2 Preprocessing Strategies 429\u003c\/p\u003e \u003cp\u003e15.3.3 Handling Class Imbalance 429\u003c\/p\u003e \u003cp\u003e15.3.4 Adversarial Training and Evaluation 429\u003c\/p\u003e \u003cp\u003e15.4 Results and Insights 431\u003c\/p\u003e \u003cp\u003e15.4.1 Experimental Setup 431\u003c\/p\u003e \u003cp\u003e15.4.2 Performance Analysis 435\u003c\/p\u003e \u003cp\u003e15.4.3 Performance Insights with Visualization 436\u003c\/p\u003e \u003cp\u003e15.4.4 Benchmarking Against Existing Methods 438\u003c\/p\u003e \u003cp\u003e15.4.5 Key Insights 439\u003c\/p\u003e \u003cp\u003e15.5 Feature Importance Analysis 439\u003c\/p\u003e \u003cp\u003e15.5.1 Top Feature Importance 439\u003c\/p\u003e \u003cp\u003e15.5.2 Feature Impact Analysis Using SHAP Values 441\u003c\/p\u003e \u003cp\u003e15.5.3 Global Feature Impact Distribution 442\u003c\/p\u003e \u003cp\u003e15.6 Comparative Analysis and Advancements over Existing Methods 442\u003c\/p\u003e \u003cp\u003e15.6.1 Feature Space Optimization 444\u003c\/p\u003e \u003cp\u003e15.6.2 Advances in Adversarial Robustness 445\u003c\/p\u003e \u003cp\u003e15.6.3 Performance Improvements 445\u003c\/p\u003e \u003cp\u003e15.6.4 Summary of Key Advancements 445\u003c\/p\u003e \u003cp\u003e15.7 Discussion 446\u003c\/p\u003e \u003cp\u003e15.7.1 Limitations and Future Work 446\u003c\/p\u003e \u003cp\u003e15.8 Conclusion 447\u003c\/p\u003e \u003cp\u003eReferences 447\u003c\/p\u003e \u003cp\u003e\u003cb\u003e16 Cyber-AI Supply Chain Vulnerabilities 451\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eJoanna C. S. Santos\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e16.1 Introduction 451\u003c\/p\u003e \u003cp\u003e16.2 AI\/ML Supply Chain Attacks via Untrusted Model Deserialization 452\u003c\/p\u003e \u003cp\u003e16.2.1 Model Deserialization 453\u003c\/p\u003e \u003cp\u003e16.2.2 AI\/ML Attack Scenarios 457\u003c\/p\u003e \u003cp\u003e16.3 The State-of-the-art of the AI\/ML Supply Chain 458\u003c\/p\u003e \u003cp\u003e16.3.1 Commonly Used Serialization Formats 458\u003c\/p\u003e \u003cp\u003e16.3.2 Deliberately Malicious Models Published on Hugging Face 460\u003c\/p\u003e \u003cp\u003e16.3.3 Developers’ Perception on Safetensors 462\u003c\/p\u003e \u003cp\u003e16.4 Conclusion 466\u003c\/p\u003e \u003cp\u003e16.4.1 Implications for Research 466\u003c\/p\u003e \u003cp\u003e16.4.2 Implications for Practitioners 467\u003c\/p\u003e \u003cp\u003eReferences 467\u003c\/p\u003e \u003cp\u003e\u003cb\u003e17 AI-powered Physical Layer Security in Industrial Wireless Networks 471\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eHong Wen, Qi Wang, and Zhibo Pang\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e17.1 Introduction 471\u003c\/p\u003e \u003cp\u003e17.2 Radio Frequency Fingerprint Identification 474\u003c\/p\u003e \u003cp\u003e17.2.1 System Model 474\u003c\/p\u003e \u003cp\u003e17.2.2 Cross-device RFFI 476\u003c\/p\u003e \u003cp\u003e17.2.3 Experimental Investigation 480\u003c\/p\u003e \u003cp\u003e17.3 CSI-based PLA 481\u003c\/p\u003e \u003cp\u003e17.3.1 System Model 482\u003c\/p\u003e \u003cp\u003e17.3.2 Transfer Learning-based PLA 484\u003c\/p\u003e \u003cp\u003e17.3.3 Data Augmentation 488\u003c\/p\u003e \u003cp\u003e17.3.4 Experimental Investigation 490\u003c\/p\u003e \u003cp\u003e17.4 PLK Distribution 493\u003c\/p\u003e \u003cp\u003e17.4.1 System Model 493\u003c\/p\u003e \u003cp\u003e17.4.2 AI-powered Quantization 495\u003c\/p\u003e \u003cp\u003e17.5 Physical Layer Security Enhanced ZT Security Framework 498\u003c\/p\u003e \u003cp\u003e17.5.1 ZT Requirements in IIoT 499\u003c\/p\u003e \u003cp\u003e17.5.2 PLS Enhanced ZT Security Framework 500\u003c\/p\u003e \u003cp\u003eReferences 502\u003c\/p\u003e \u003cp\u003e\u003cb\u003e18 The Security of Reinforcement Learning Systems in Electric Grid Domain 505\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eSuman Rath, Zain ul Abdeen, Olivera Kotevska, Viktor Reshniak, and Vivek Kumar Singh\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e18.1 Introduction 505\u003c\/p\u003e \u003cp\u003e18.2 RL for Control 506\u003c\/p\u003e \u003cp\u003e18.2.1 Overview of RL Algorithms 506\u003c\/p\u003e \u003cp\u003e18.2.2 DQN Algorithm 510\u003c\/p\u003e \u003cp\u003e18.3 Case Study: RL for Control in Cyber-physical Microgrids 513\u003c\/p\u003e \u003cp\u003e18.4 Related Work: Grid Applications of RL 516\u003c\/p\u003e \u003cp\u003e18.5 Open Challenges and Solutions 518\u003c\/p\u003e \u003cp\u003e18.6 Conclusion 522\u003c\/p\u003e \u003cp\u003eAcknowledgments 524\u003c\/p\u003e \u003cp\u003eReferences 524\u003c\/p\u003e \u003cp\u003e\u003cb\u003e19 Geopolitical Dimensions of AI in Cybersecurity: The Emerging Battleground 533\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eFelix Staicu and Mihai Barloiu\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e19.1 Introduction 533\u003c\/p\u003e \u003cp\u003e19.1.1 A Conceptual Framework 534\u003c\/p\u003e \u003cp\u003e19.2 Foundations of AI in Geopolitics: From Military Origins to Emerging Strategic Trajectories 536\u003c\/p\u003e \u003cp\u003e19.2.1 Historical Foundations: The Military and Intelligence Roots of Key Technologies 536\u003c\/p\u003e \u003cp\u003e19.2.2 Early International Debates on AI Governance and Their Geopolitical Dimensions 537\u003c\/p\u003e \u003cp\u003e19.2.3 The Two-way Influence Between AI and Geopolitics: Early Signals of Strategic Catalysts and Normative Vectors 538\u003c\/p\u003e \u003cp\u003e19.3 The Contemporary Battleground: AI as a Strategic Variable 540\u003c\/p\u003e \u003cp\u003e19.3.1 AI-infused IO: Precision, Persistence, and Policy Dilemmas 540\u003c\/p\u003e \u003cp\u003e19.3.2 Fusion Technologies for Battlefield Control, Unmanned Vehicles, and AI Swarming 542\u003c\/p\u003e \u003cp\u003e19.3.3 Regulatory Power as Soft Power: Competing Models for Global AI Norms 543\u003c\/p\u003e \u003cp\u003e19.3.4 Global Rivalries: The US-China AI Race and the Fragmenting Digital Ecosystem 545\u003c\/p\u003e \u003cp\u003e19.4 Beyond Today’s Conflicts: Future Horizons in AI-driven Security 548\u003c\/p\u003e \u003cp\u003e19.4.1 2050 Hypothesis-driven Scenarios in the International System 548\u003c\/p\u003e \u003cp\u003e19.4.2 AI in the Nuclear Quartet 551\u003c\/p\u003e \u003cp\u003e19.4.3 AI in Kinetic Conventional Military Capabilities 553\u003c\/p\u003e \u003cp\u003e19.4.4 AI in Cybersecurity and Information Warfare 554\u003c\/p\u003e \u003cp\u003e19.4.5 A Holistic View of AI’s Impact on International Security 556\u003c\/p\u003e \u003cp\u003e19.5 Conclusions and Recommendations 558\u003c\/p\u003e \u003cp\u003e19.5.1 Integrative Insights 558\u003c\/p\u003e \u003cp\u003e19.6 Conclusion 560\u003c\/p\u003e \u003cp\u003eAcknowledgments 561\u003c\/p\u003e \u003cp\u003eReferences 561\u003c\/p\u003e \u003cp\u003e\u003cb\u003e20 Robust AI Techniques to Support High-consequence Applications in the Cyber Age 567\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eJoel Brogan, Linsey Passarella, Mark Adam, Birdy Phathanapirom, Nathan Martindale, Jordan Stomps, Olivera Kotevska, Matthew Yohe, Ryan Tokola, Ryan Kerekes, and Scott Stewart\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e20.1 Introduction 567\u003c\/p\u003e \u003cp\u003e20.2 Motivation 568\u003c\/p\u003e \u003cp\u003e20.3 Explainability Measures for Deep Learning in High-consequence Scenarios 570\u003c\/p\u003e \u003cp\u003e20.3.1 Gradient-based Methods 571\u003c\/p\u003e \u003cp\u003e20.3.2 Perturbation-based Methods 572\u003c\/p\u003e \u003cp\u003e20.3.3 Comparisons Between Explainability Methods 572\u003c\/p\u003e \u003cp\u003e20.4 Improving Confidence and Robustness Measures for Deep Learning in Critical Decision-making Scenarios 573\u003c\/p\u003e \u003cp\u003e20.4.1 Introduction 573\u003c\/p\u003e \u003cp\u003e20.4.2 Dataset Description 574\u003c\/p\u003e \u003cp\u003e20.4.3 Methodology 575\u003c\/p\u003e \u003cp\u003e20.4.4 Attribution Algorithms 576\u003c\/p\u003e \u003cp\u003e20.4.5 Confidence Measure Algorithms 576\u003c\/p\u003e \u003cp\u003e20.4.6 Results and Analysis 581\u003c\/p\u003e \u003cp\u003e20.4.7 Discussion and Future Work 581\u003c\/p\u003e \u003cp\u003e20.5 Building Robust AI Through SME Knowledge Embeddings 583\u003c\/p\u003e \u003cp\u003e20.5.1 Explicit Knowledge in Structured Formats 586\u003c\/p\u003e \u003cp\u003e20.5.2 Fine-tuning and Evaluating Foundation Models 587\u003c\/p\u003e \u003cp\u003e20.6 Flight-path Vocabularies for Foundation Model Training 588\u003c\/p\u003e \u003cp\u003e20.6.1 Introduction 588\u003c\/p\u003e \u003cp\u003e20.6.2 Dataset 589\u003c\/p\u003e \u003cp\u003e20.6.3 Methodology 590\u003c\/p\u003e \u003cp\u003e20.6.4 Results and Discussion 591\u003c\/p\u003e \u003cp\u003e20.7 Promise and Peril of Foundation Models in High-consequence Scenarios 592\u003c\/p\u003e \u003cp\u003e20.7.1 Adversarial Vulnerabilities of Foundation Models 593\u003c\/p\u003e \u003cp\u003e20.7.2 Privacy Violation Vulnerabilities in Foundation Models 594\u003c\/p\u003e \u003cp\u003e20.7.3 Alignment Hazards When Training Foundation Models 594\u003c\/p\u003e \u003cp\u003e20.7.4 Performance Hazards When Inferring and Generating with Foundation Models 595\u003c\/p\u003e \u003cp\u003e20.8 Discussion 596\u003c\/p\u003e \u003cp\u003eAcknowledgments 596\u003c\/p\u003e \u003cp\u003eReferences 596\u003c\/p\u003e \u003cp\u003eIndex 601\u003c\/p\u003e\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eSubject Areas: Computer science [\u003ca title=\"See our other books on Computer science\" href=\"https:\/\/freshlyprintedbooks.co.uk\/search?q=%22Computer%20science%20%5BUY%5D%22\"\u003eUY\u003c\/a\u003e]\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003c\/font\u003e","brand":"Wiley-IEEE Press","offers":[{"title":"Brand New","offer_id":52433306648856,"sku":"9781394293742","price":96.49,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9781394293742.jpg?v=1784853183","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/ai-for-cybersecurity-research-and-practice-hardback-9781394293742","provider":"Freshly Printed Books","version":"1.0","type":"link"}