{"product_id":"adversarial-machine-learning-mechanisms-vulnerabilities-and-strategies-for-trustworthy-ai-hardback-9781394402038","title":"Adversarial Machine Learning; Mechanisms, Vulnerabilities, and Strategies for Trustworthy AI (Hardback) 9781394402038","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eAdversarial Machine Learning\u003c\/font\u003e\u003cbr\u003e\r\n\u003cfont size=\"5\"\u003eMechanisms, Vulnerabilities, and Strategies for Trustworthy AI\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\u003cp\u003e\u003cfont size=\"4\"\u003eJason Edwards (Author)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9781394402038, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eHardback, published 19 February 2026\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e400 pages\u003cbr\u003e26 x 18.4 x 3 cm, 0.879 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\u003eEnables readers to understand the full lifecycle of adversarial machine learning (AML) and how AI models can be compromised\u003c\/b\u003e \u003c\/p\u003e\n\u003cp\u003e\u003ci\u003eAdversarial Machine Learning\u003c\/i\u003e is a definitive guide to one of the most urgent challenges in artificial intelligence today: how to secure machine learning systems against adversarial threats. \u003c\/p\u003e\n\u003cp\u003eThis book explores the full lifecycle of adversarial machine learning (AML), providing a structured, real-world understanding of how AI models can be compromised—and what can be done about it. \u003c\/p\u003e\n\u003cp\u003eThe book walks readers through the different phases of the machine learning pipeline, showing how attacks emerge during training, deployment, and inference. It breaks down adversarial threats into clear categories based on attacker goals—whether to disrupt system availability, tamper with outputs, or leak private information. With clarity and technical rigor, it dissects the tools, knowledge, and access attackers need to exploit AI systems. \u003c\/p\u003e\n\u003cp\u003eIn addition to diagnosing threats, the book provides a robust overview of defense strategies—from adversarial training and certified defenses to privacy-preserving machine learning and risk-aware system design. Each defense is discussed alongside its limitations, trade-offs, and real-world applicability. \u003c\/p\u003e\n\u003cp\u003eReaders will gain a comprehensive view of today???s most dangerous attack methods including: \u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eEvasion attacks that manipulate inputs to deceive AI predictions \u003c\/li\u003e \u003cli\u003ePoisoning attacks that corrupt training data or model updates \u003c\/li\u003e \u003cli\u003eBackdoor and trojan attacks that embed malicious triggers\u003c\/li\u003e \u003cli\u003ePrivacy attacks that reveal sensitive data through model interaction and prompt injection\u003c\/li\u003e \u003cli\u003eGenerative AI attacks that exploit the new wave of large language models\u003c\/li\u003e \u003c\/ul\u003e\n\u003cp\u003eBlending technical depth with practical insight, \u003ci\u003eAdversarial Machine Learning\u003c\/i\u003e equips developers, security engineers, and AI decision-makers with the knowledge they need to understand the adversarial landscape and defend their systems with confidence.\u003c\/p\u003e\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003ePreface xi\u003c\/p\u003e \u003cp\u003eAcknowledgments xiii\u003c\/p\u003e \u003cp\u003eFrom the Author xv\u003c\/p\u003e \u003cp\u003eIntroduction xvii\u003c\/p\u003e \u003cp\u003eAbout the Companion Website xxi\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 The Age of Intelligent Threats 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Rise of AI as a Security Target 1\u003c\/p\u003e \u003cp\u003eFragility in Intelligent Systems 3\u003c\/p\u003e \u003cp\u003eCategories of AI: Predictive, Generative, and Agentic 5\u003c\/p\u003e \u003cp\u003eMilestones in Adversarial Vulnerability 8\u003c\/p\u003e \u003cp\u003eIntelligence as an Attack Multiplier 10\u003c\/p\u003e \u003cp\u003eWhy This Book and Who It’s For 12\u003c\/p\u003e \u003cp\u003eRecommendations 14\u003c\/p\u003e \u003cp\u003eConclusion 16\u003c\/p\u003e \u003cp\u003eKey Concepts 16\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 Anatomy of AI Systems and Their Attack Surfaces 21\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Architecture of Predictive, Generative, and Agentic AI 21\u003c\/p\u003e \u003cp\u003eThe AI Development Lifecycle: From Data to Deployment 24\u003c\/p\u003e \u003cp\u003eClassical Machine Learning vs. Modern AI Pipelines 26\u003c\/p\u003e \u003cp\u003eIdentifying Entry Points: Training, Inference, and Supply Chain 28\u003c\/p\u003e \u003cp\u003eSecurity Debt in the Model Development Lifecycle 31\u003c\/p\u003e \u003cp\u003eRecommendations 33\u003c\/p\u003e \u003cp\u003eConclusion 35\u003c\/p\u003e \u003cp\u003eKey Concepts 35\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 The Adversary’s Playbook 39\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThreat Actors: Profiles, Motivations, and Objectives 39\u003c\/p\u003e \u003cp\u003eWhite-Box Attack Techniques and Methodologies 41\u003c\/p\u003e \u003cp\u003eBlack-Box Attack Techniques and Methodologies 44\u003c\/p\u003e \u003cp\u003eGray-Box Attack Techniques and Methodologies 47\u003c\/p\u003e \u003cp\u003eOperationalizing AI Attacks: Tactical Methodologies and Execution 49\u003c\/p\u003e \u003cp\u003eAdvanced Multi-Stage and Coordinated AI Attacks 52\u003c\/p\u003e \u003cp\u003eRecommendations 54\u003c\/p\u003e \u003cp\u003eConclusion 55\u003c\/p\u003e \u003cp\u003eKey Concepts 56\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Evasion Attacks—Tricking AI Models at Inference 61\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eCore Principles and Mechanisms of Evasion Attacks 61\u003c\/p\u003e \u003cp\u003eGradient-Based Evasion Techniques 64\u003c\/p\u003e \u003cp\u003eLinguistic and Textual Evasion Methods 67\u003c\/p\u003e \u003cp\u003eImage- and Vision-Based Evasion Techniques 69\u003c\/p\u003e \u003cp\u003eEvasion Attacks on Time-Series and Sequential Models 72\u003c\/p\u003e \u003cp\u003eRecommendations 74\u003c\/p\u003e \u003cp\u003eConclusion 76\u003c\/p\u003e \u003cp\u003eKey Concepts 76\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Poisoning Attacks—Compromising AI Systems During Training 81\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eFundamentals and Mechanisms of Training-Time Poisoning 81\u003c\/p\u003e \u003cp\u003eLabel Manipulation and Clean-Label Poisoning Techniques 84\u003c\/p\u003e \u003cp\u003eBackdoor and Trojan Insertion in Training Data 86\u003c\/p\u003e \u003cp\u003ePoisoning Attacks on Federated and Distributed Learning Systems 89\u003c\/p\u003e \u003cp\u003ePoisoning Attacks Against Reinforcement Learning (RL) Systems 91\u003c\/p\u003e \u003cp\u003ePoisoning Attacks on Transfer Learning and Fine-Tuning Processes 94\u003c\/p\u003e \u003cp\u003eRecommendations 96\u003c\/p\u003e \u003cp\u003eConclusion 98\u003c\/p\u003e \u003cp\u003eKey Concepts 98\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Privacy Attacks—Extracting Secrets from AI Models 103\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eCore Mechanisms and Objectives of AI Privacy Attacks 103\u003c\/p\u003e \u003cp\u003eMembership Inference Techniques 106\u003c\/p\u003e \u003cp\u003eModel Inversion Attacks and Data Reconstruction 109\u003c\/p\u003e \u003cp\u003eAttribute and Property Inference Attacks 111\u003c\/p\u003e \u003cp\u003eModel Extraction and Functionality Reconstruction 114\u003c\/p\u003e \u003cp\u003eExploiting Privacy Leakage Through Prompting Generative AI 117\u003c\/p\u003e \u003cp\u003eRecommendations 119\u003c\/p\u003e \u003cp\u003eConclusion 120\u003c\/p\u003e \u003cp\u003eKey Concepts 121\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Backdoor and Trojan Attacks—Embedding Hidden Behaviors in AI Models 125\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eFundamental Concepts of AI Backdoors and Trojans 125\u003c\/p\u003e \u003cp\u003eBackdoor Trigger Design and Optimization 128\u003c\/p\u003e \u003cp\u003eData Poisoning Methods for Backdoor Embedding 130\u003c\/p\u003e \u003cp\u003eTrojan Attacks in Transfer and Fine-Tuning Scenarios 132\u003c\/p\u003e \u003cp\u003eEmbedding Backdoors in Federated and Decentralized Training 135\u003c\/p\u003e \u003cp\u003eAdvanced Trigger Embedding in Generative and Agentic AI Models 137\u003c\/p\u003e \u003cp\u003eRecommendations 140\u003c\/p\u003e \u003cp\u003eConclusion 141\u003c\/p\u003e \u003cp\u003eKey Concepts 142\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 The Generative AI Attack Surface 147\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eArchitectural Foundations of Large Language Models 147\u003c\/p\u003e \u003cp\u003eHow Generative Architectures Expand Attack Opportunities 150\u003c\/p\u003e \u003cp\u003eExploiting Fine-Tuning as an Adversarial Vector 152\u003c\/p\u003e \u003cp\u003ePrompt Engineering as an Adversarial Exploitation Pathway 155\u003c\/p\u003e \u003cp\u003eTechnical Risks in Retrieval-Augmented Generation Systems 157\u003c\/p\u003e \u003cp\u003eLeveraging Model Internals for Generative AI Exploitation 160\u003c\/p\u003e \u003cp\u003eRecommendations 163\u003c\/p\u003e \u003cp\u003eConclusion 164\u003c\/p\u003e \u003cp\u003eKey Concepts 165\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Prompt Injection and Jailbreak Techniques 169\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Foundations of Prompt Injection Attacks 169\u003c\/p\u003e \u003cp\u003eDirect Prompt Injection Methods and Input Crafting 173\u003c\/p\u003e \u003cp\u003eIndirect Prompt Injection via External or Retrieved Content 175\u003c\/p\u003e \u003cp\u003eJailbreak Techniques and Semantic Boundary Exploitation 177\u003c\/p\u003e \u003cp\u003eToken-Level and Embedding Space Manipulations 180\u003c\/p\u003e \u003cp\u003eContextual and Conversational Injection Strategies 182\u003c\/p\u003e \u003cp\u003eRecommendations 185\u003c\/p\u003e \u003cp\u003eConclusion 186\u003c\/p\u003e \u003cp\u003eKey Concepts 187\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 Data Leakage and Model Hallucination 191\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Mechanisms of Data Leakage in Generative Models 191\u003c\/p\u003e \u003cp\u003eMembership and Attribute Inference via Generative Outputs 195\u003c\/p\u003e \u003cp\u003eModel Inversion and Training Data Reconstruction 197\u003c\/p\u003e \u003cp\u003eHallucination Exploitation in Generative Outputs 199\u003c\/p\u003e \u003cp\u003ePrompt-Based Extraction of Memorized Data 202\u003c\/p\u003e \u003cp\u003eExploiting Multi-Modal and Cross-Modal Leakage in Generative Models 204\u003c\/p\u003e \u003cp\u003eRecommendations 207\u003c\/p\u003e \u003cp\u003eConclusion 208\u003c\/p\u003e \u003cp\u003eKey Concepts 209\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Adversarial Fine-Tuning and Model Reprogramming 213\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Foundations of Adversarial Fine-Tuning 213\u003c\/p\u003e \u003cp\u003eSemantic Perturbation Methods for Adversarial Fine-Tuning 216\u003c\/p\u003e \u003cp\u003eEmbedding Covert Behaviors via Adversarial Prompt Conditioning 219\u003c\/p\u003e \u003cp\u003eAdvanced Trojan Embedding via Fine-Tuning Gradients 221\u003c\/p\u003e \u003cp\u003eCross-Model and Transferable Adversarial Fine-Tuning Attacks 223\u003c\/p\u003e \u003cp\u003eModel Reprogramming via Adversarial Fine-Tuning Techniques 226\u003c\/p\u003e \u003cp\u003eRecommendations 228\u003c\/p\u003e \u003cp\u003eConclusion 229\u003c\/p\u003e \u003cp\u003eKey Concepts 230\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 Agentic AI and Autonomous Threat Loops 235\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Foundations of Agentic AI Systems 235\u003c\/p\u003e \u003cp\u003eTechnical Manipulation of Autonomous Decision Loops 238\u003c\/p\u003e \u003cp\u003eExploitation of Agentic Memory and Context Management 241\u003c\/p\u003e \u003cp\u003eAgentic Tool Integration and External API Exploitation 244\u003c\/p\u003e \u003cp\u003eTechnical Embedding of Autonomous Chain Injection 246\u003c\/p\u003e \u003cp\u003eExploitation of Environmental Interactions and Stateful Vulnerabilities 248\u003c\/p\u003e \u003cp\u003eRecommendations 251\u003c\/p\u003e \u003cp\u003eConclusion 252\u003c\/p\u003e \u003cp\u003eKey Concepts 253\u003c\/p\u003e \u003cp\u003e\u003cb\u003e13 Securing the AI Supply Chain 257\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Mechanisms of Supply Chain Poisoning in AI Models 257\u003c\/p\u003e \u003cp\u003eArtifact and Model Checkpoint Contamination Techniques 260\u003c\/p\u003e \u003cp\u003eTechnical Exploitation of Third-Party AI Libraries and Frameworks 263\u003c\/p\u003e \u003cp\u003eDataset Provenance and Annotation Manipulation Techniques 265\u003c\/p\u003e \u003cp\u003eTechnical Exploitation of Hosted and Cloud-based Model Infrastructure 268\u003c\/p\u003e \u003cp\u003eArtifact Repositories and Model Zoo Contamination Methods 270\u003c\/p\u003e \u003cp\u003eRecommendations 272\u003c\/p\u003e \u003cp\u003eConclusion 273\u003c\/p\u003e \u003cp\u003eKey Concepts 274\u003c\/p\u003e \u003cp\u003e\u003cb\u003e14 Evaluating AI Robustness and Response Strategies 277\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Foundations of AI Robustness Evaluation 277\u003c\/p\u003e \u003cp\u003eMetrics for Evaluating AI Security and Robustness 279\u003c\/p\u003e \u003cp\u003eRobust Optimization Methods and Adversarial Training 282\u003c\/p\u003e \u003cp\u003eCertified Robustness and Formal Verification Techniques 285\u003c\/p\u003e \u003cp\u003eTechnical Benchmarking Tools and Evaluation Frameworks 287\u003c\/p\u003e \u003cp\u003eTechnical Analysis of Robustness Across Model Architectures and Modalities 289\u003c\/p\u003e \u003cp\u003eRecommendations 292\u003c\/p\u003e \u003cp\u003eConclusion 293\u003c\/p\u003e \u003cp\u003eKey Concepts 294\u003c\/p\u003e \u003cp\u003e\u003cb\u003e15 Building Trustworthy AI by Design 299\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Foundations of Security-by-Design in AI Systems 299\u003c\/p\u003e \u003cp\u003eRobust Embedding and Representation Learning Methods 302\u003c\/p\u003e \u003cp\u003eTechnical Approaches to Adversarially Robust Architectures 304\u003c\/p\u003e \u003cp\u003eTechnical Integration of Formal Verification in Model Design 306\u003c\/p\u003e \u003cp\u003eTechnical Frameworks for Runtime Anomaly Detection and Filtering 308\u003c\/p\u003e \u003cp\u003eTechnical Embedding of Model Interpretability and Transparency 310\u003c\/p\u003e \u003cp\u003eRecommendations 313\u003c\/p\u003e \u003cp\u003eConclusion 315\u003c\/p\u003e \u003cp\u003eKey Concepts 315\u003c\/p\u003e \u003cp\u003e\u003cb\u003e16 Looking Ahead—Security in the Era of Intelligent Agents 319\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTechnical Foundations of Future Agentic AI Systems 319\u003c\/p\u003e \u003cp\u003eEmerging Technical Attack Vectors in Agentic Systems 322\u003c\/p\u003e \u003cp\u003eTechnical Exploitation of Multi-Modal and Cross-Domain Agentic Capabilities 325\u003c\/p\u003e \u003cp\u003eFuture Technical Capabilities in Automated Adversarial Generation 327\u003c\/p\u003e \u003cp\u003eTechnical Mechanisms for Evaluating Advanced Agentic Robustness 330\u003c\/p\u003e \u003cp\u003eTechnical Embedding of Ethical Constraints and Safety Mechanisms 332\u003c\/p\u003e \u003cp\u003eRecommendations 335\u003c\/p\u003e \u003cp\u003eConclusion 337\u003c\/p\u003e \u003cp\u003eKey Concepts 337\u003c\/p\u003e \u003cp\u003eGlossary 341\u003c\/p\u003e \u003cp\u003eIndex 367\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","offers":[{"title":"Brand New","offer_id":52503014408472,"sku":"9781394402038","price":60.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9781394402038.jpg?v=1786323928","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/adversarial-machine-learning-mechanisms-vulnerabilities-and-strategies-for-trustworthy-ai-hardback-9781394402038","provider":"Freshly Printed Books","version":"1.0","type":"link"}