Primary Navigation
Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.
Book Contents Navigation
Acknowledgements
About this Book
Book Navigation
1.0 Learning Outcomes
1.1 Introduction to Machine Learning Security
1.2 Adversarial Attack Types: Model Processing and Development
1.3 Adversarial Attack Types: Knowledge of Adversary
1.4 Adversarial Attack Types: Capability and Intention of the Adversary.
1.5 Key Concepts in Machine Learning Security
1.6 Challenges in Securing Machine Learning Systems
1.7 Chapter Summary
1.8 End of Chapter Activities
2.0 Learning Outcomes
2.1 Introduction
2.2 Categories of Attacks
2.3 Adaptive Interplay in ML Security
2.4 Adversary’s Model and Attack Scenario
2.5 Attack Scenarios
2.6 Key Components of Threat Models in ML
2.7 Conclusion: The Future of the AI Arms Race
2.8 Chapter Summary
2.9 End of Chapter Activities
2.10 Case Study: The Evolving Threat Landscape of ChatGPT - A Security Arms Race
3.0 Learning Outcomes
3.1 Introduction
3.2 Why Are We Interested in Adversarial Examples?
3.3 Common Terms
3.4 Distance Metrics of Adversarial Perturbations
3.5 Methods and Examples
3.6 Adversarial Example in Physical World
3.7 Mitigating Evasion Attack
3.8 Chapter Summary
3.9 End of Chapter Activities
4.0 Learning Outcomes
4.1 Introduction
4.2 Why Are We Concerned About Poisoning Attacks?
4.3 Attack Method and Examples
4.4 Mitigating Poisoning Attacks
4.5 Chapter Summary
4.6 End of Chapter Activities
5.0 Learning Outcomes
5.1 Introduction
5.2 How Backdoor Poisoning Works
5.3 Backdoor Attack Scenarios
5.4 Types of Backdoor Attacks
5.5 Mitigating Backdoor Attacks
5.6 Defences for Federated Learning
5.7 Chapter Summary
5.8 End of Chapter Activities
6.0 Learning Outcomes
6.1 Introduction
6.2 Types of Privacy Attacks
6.3 Mitigation Strategies
6.4 Chapter Summary
6.5 End of Chapter Activities
Version History
Reference List
6.0 Learning Outcomes 6.1 Introduction 6.2 Types of Privacy Attacks 6.3 Mitigation Strategies 6.4 Chapter Summary 6.5 End of Chapter Activities
Previous/next navigation
Winning the Battle for Secure ML Copyright © 2025 by Bestan Maaroof is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License, except where otherwise noted.