Adversarial Machine Learning : Mechanisms, Vulnerabilities, and Strategies for Trustworthy AI.

Format:

Book

Author/Creator:

Edwards, Jason.

Language:

English

Subjects (All):

Machine learning.

Artificial intelligence.

Computer security.

Cryptography.

Physical Description:

1 online resource (502 pages)

Edition:

1st ed.

Place of Publication:

Newark : John Wiley & Sons, Incorporated, 2026.

Summary:

Enables readers to understand the full lifecycle of adversarial machine learning (AML) and how AI models can be compromised Adversarial Machine Learning is a definitive guide to one of the most urgent challenges in artificial intelligence today: how to secure machine learning systems against adversarial threats.

Contents:

Cover

Title Page

Copyright

Contents

Preface

Acknowledgments

From the Author

Introduction

About the Companion Website

Chapter 1 The Age of Intelligent Threats

The Rise of AI as a Security Target

Fragility in Intelligent Systems

Categories of AI: Predictive, Generative, and Agentic

Milestones in Adversarial Vulnerability

Intelligence as an Attack Multiplier

Why This Book and Who It's For

Recommendations

Conclusion

Key Concepts

Essential Terms in Context

Adversary Spotlight

Common Misunderstandings

Defense Framing

Chapter 2 Anatomy of AI Systems and Their Attack Surfaces

The Architecture of Predictive, Generative, and Agentic AI

The AI Development Lifecycle: From Data to Deployment

Classical Machine Learning vs. Modern AI Pipelines

Identifying Entry Points: Training, Inference, and Supply Chain

Security Debt in the Model Development Lifecycle

Chapter 3 The Adversary's Playbook

Threat Actors: Profiles, Motivations, and Objectives

White‐Box Attack Techniques and Methodologies

Black‐Box Attack Techniques and Methodologies

Gray‐Box Attack Techniques and Methodologies

Operationalizing AI Attacks: Tactical Methodologies and Execution

Advanced Multi‐Stage and Coordinated AI Attacks

Chapter 4 Evasion Attacks-Tricking AI Models at Inference

Core Principles and Mechanisms of Evasion Attacks

Gradient‐Based Evasion Techniques

Linguistic and Textual Evasion Methods

Image‐ and Vision‐Based Evasion Techniques.

Evasion Attacks on Time‐Series and Sequential Models

Chapter 5 Poisoning Attacks-Compromising AI Systems During Training

Fundamentals and Mechanisms of Training‐Time Poisoning

Label Manipulation and Clean‐Label Poisoning Techniques

Backdoor and Trojan Insertion in Training Data

Poisoning Attacks on Federated and Distributed Learning Systems

Poisoning Attacks Against Reinforcement Learning (RL) Systems

Poisoning Attacks on Transfer Learning and Fine‐Tuning Processes

Chapter 6 Privacy Attacks-Extracting Secrets from AI Models

Core Mechanisms and Objectives of AI Privacy Attacks

Membership Inference Techniques

Model Inversion Attacks and Data Reconstruction

Attribute and Property Inference Attacks

Model Extraction and Functionality Reconstruction

Exploiting Privacy Leakage Through Prompting Generative AI

Chapter 7 Backdoor and Trojan Attacks-Embedding Hidden Behaviors in AI Models

Fundamental Concepts of AI Backdoors and Trojans

Backdoor Trigger Design and Optimization

Data Poisoning Methods for Backdoor Embedding

Trojan Attacks in Transfer and Fine‐Tuning Scenarios

Embedding Backdoors in Federated and Decentralized Training

Advanced Trigger Embedding in Generative and Agentic AI Models

Defense Framing.

Chapter 8 The Generative AI Attack Surface

Architectural Foundations of Large Language Models

How Generative Architectures Expand Attack Opportunities

Exploiting Fine‐Tuning as an Adversarial Vector

Prompt Engineering as an Adversarial Exploitation Pathway

Technical Risks in Retrieval‐Augmented Generation Systems

Leveraging Model Internals for Generative AI Exploitation

Chapter 9 Prompt Injection and Jailbreak Techniques

Technical Foundations of Prompt Injection Attacks

Direct Prompt Injection Methods and Input Crafting

Indirect Prompt Injection via External or Retrieved Content

Jailbreak Techniques and Semantic Boundary Exploitation

Token‐Level and Embedding Space Manipulations

Contextual and Conversational Injection Strategies

Chapter 10 Data Leakage and Model Hallucination

Technical Mechanisms of Data Leakage in Generative Models

Membership and Attribute Inference via Generative Outputs

Model Inversion and Training Data Reconstruction

Hallucination Exploitation in Generative Outputs

Prompt‐Based Extraction of Memorized Data

Exploiting Multi‐Modal and Cross‐Modal Leakage in Generative Models

Chapter 11 Adversarial Fine‐Tuning and Model Reprogramming

Technical Foundations of Adversarial Fine‐Tuning

Semantic Perturbation Methods for Adversarial Fine‐Tuning

Embedding Covert Behaviors via Adversarial Prompt Conditioning.

Advanced Trojan Embedding via Fine‐Tuning Gradients

Cross‐Model and Transferable Adversarial Fine‐Tuning Attacks

Model Reprogramming via Adversarial Fine‐Tuning Techniques

Chapter 12 Agentic AI and Autonomous Threat Loops

Technical Foundations of Agentic AI Systems

Technical Manipulation of Autonomous Decision Loops

Exploitation of Agentic Memory and Context Management

Agentic Tool Integration and External API Exploitation

Technical Embedding of Autonomous Chain Injection

Exploitation of Environmental Interactions and Stateful Vulnerabilities

Chapter 13 Securing the AI Supply Chain

Technical Mechanisms of Supply Chain Poisoning in AI Models

Artifact and Model Checkpoint Contamination Techniques

Technical Exploitation of Third‐Party AI Libraries and Frameworks

Dataset Provenance and Annotation Manipulation Techniques

Technical Exploitation of Hosted and Cloud‐based Model Infrastructure

Artifact Repositories and Model Zoo Contamination Methods

Chapter 14 Evaluating AI Robustness and Response Strategies

Technical Foundations of AI Robustness Evaluation

Metrics for Evaluating AI Security and Robustness

Robust Optimization Methods and Adversarial Training

Certified Robustness and Formal Verification Techniques

Technical Benchmarking Tools and Evaluation Frameworks

Technical Analysis of Robustness Across Model Architectures and Modalities.

Recommendations

Chapter 15 Building Trustworthy AI by Design

Technical Foundations of Security‐by‐Design in AI Systems

Robust Embedding and Representation Learning Methods

Technical Approaches to Adversarially Robust Architectures

Technical Integration of Formal Verification in Model Design

Technical Frameworks for Runtime Anomaly Detection and Filtering

Technical Embedding of Model Interpretability and Transparency

Chapter 16 Looking Ahead-Security in the Era of Intelligent Agents

Technical Foundations of Future Agentic AI Systems

Emerging Technical Attack Vectors in Agentic Systems

Technical Exploitation of Multi‐Modal and Cross‐Domain Agentic Capabilities

Future Technical Capabilities in Automated Adversarial Generation

Technical Mechanisms for Evaluating Advanced Agentic Robustness

Technical Embedding of Ethical Constraints and Safety Mechanisms

Glossary

Index

EULA.

Notes:

Electronic book.

Description based on publisher supplied metadata and other sources.

ISBN:

1-394-40206-6

1-394-40204-X

9781394402045

OCLC:

1567471484