Adversarial Machine Learning - Jason Edwards

. .

Résumé :

Preface xi

Acknowledgments xiii

From the Author xv

Introduction xvii

About the Companion Website xxi

1 The Age of Intelligent Threats 1

The Rise of AI as a Security Target 1

Fragility in Intelligent Systems 3

Categories of AI: Predictive, Generative, and Agentic 5

Milestones in Adversarial Vulnerability 8

Intelligence as an Attack Multiplier 10

Why This Book and Who It's For 12

Recommendations 14

Conclusion 16

Key Concepts 16

2 Anatomy of AI Systems and Their Attack Surfaces 21

The Architecture of Predictive, Generative, and Agentic AI 21

The AI Development Lifecycle: From Data to Deployment 24

Classical Machine Learning vs. Modern AI Pipelines 26

Identifying Entry Points: Training, Inference, and Supply Chain 28

Security Debt in the Model Development Lifecycle 31

Recommendations 33

Conclusion 35

Key Concepts 35

3 The Adversary's Playbook 39

Threat Actors: Profiles, Motivations, and Objectives 39

White-Box Attack Techniques and Methodologies 41

Black-Box Attack Techniques and Methodologies 44

Gray-Box Attack Techniques and Methodologies 47

Operationalizing AI Attacks: Tactical Methodologies and Execution 49

Advanced Multi-Stage and Coordinated AI Attacks 52

Recommendations 54

Conclusion 55

Key Concepts 56

4 Evasion Attacks-Tricking AI Models at Inference 61

Core Principles and Mechanisms of Evasion Attacks 61

Gradient-Based Evasion Techniques 64

Linguistic and Textual Evasion Methods 67

Image- and Vision-Based Evasion Techniques 69

Evasion Attacks on Time-Series and Sequential Models 72

Recommendations 74

Conclusion 76

Key Concepts 76

5 Poisoning Attacks-Compromising AI Systems During Training 81

Fundamentals and Mechanisms of Training-Time Poisoning 81

Label Manipulation and Clean-Label Poisoning Techniques 84

Backdoor and Trojan Insertion in Training Data 86

Poisoning Attacks on Federated and Distributed Learning Systems 89

Poisoning Attacks Against Reinforcement Learning (RL) Systems 91

Poisoning Attacks on Transfer Learning and Fine-Tuning Processes 94

Recommendations 96

Conclusion 98

Key Concepts 98

6 Privacy Attacks-Extracting Secrets from AI Models 103

Core Mechanisms and Objectives of AI Privacy Attacks 103

Membership Inference Techniques 106

Model Inversion Attacks and Data Reconstruction 109

Attribute and Property Inference Attacks 111

Model Extraction and Functionality Reconstruction 114

Exploiting Privacy Leakage Through Prompting Generative AI 117

Recommendations 119

Conclusion 120

Key Concepts 121

7 Backdoor and Trojan Attacks-Embedding Hidden Behaviors in AI Models 125

Fundamental Concepts of AI Backdoors and Trojans 125

Backdoor Trigger Design and Optimization 128

Data Poisoning Methods for Backdoor Embedding 130

Trojan Attacks in Transfer and Fine-Tuning Scenarios 132

Embedding Backdoors in Federated and Decentralized Training 135

Advanced Trigger Embedding in Generative and Agentic AI Models 137

Recommendations 140

Conclusion 141

Key Concepts 142

8 The Generative AI Attack Surface 147

Architectural Foundations of Large Language Models 147

How Generative Architectures Expand Attack Opportunities 150

Exploiting Fine-Tuning as an Adversarial Vector 152

Prompt Engineering as an Adversarial Exploitation Pathway 155

Technical...

Biographie:

Jason Edwards, DM, CISSP, is an accomplished cybersecurity leader with extensive experience in the technology, finance, insurance, and energy sectors. Holding a Doctorate in Management, Information Systems, and Technology, Jason specializes in guiding large public and private companies through complex cybersecurity challenges. His career includes leadership roles across the military, insurance, finance, energy, and technology industries. He is a husband, father, former military cyber officer, adjunct professor, avid reader, dog dad, and popular on LinkedIn.