Book Image

Adversarial AI Attacks, Mitigations, and Defense Strategies

By : John Sotiropoulos
5 (1)
Book Image

Adversarial AI Attacks, Mitigations, and Defense Strategies

5 (1)
By: John Sotiropoulos

Overview of this book

Adversarial attacks trick AI systems with malicious data, creating new security risks by exploiting how AI learns. This challenges cybersecurity as it forces us to defend against a whole new kind of threat. This book demystifies adversarial attacks and equips cybersecurity professionals with the skills to secure AI technologies, moving beyond research hype or business-as-usual strategies. The strategy-based book is a comprehensive guide to AI security, presenting a structured approach with practical examples to identify and counter adversarial attacks. This book goes beyond a random selection of threats and consolidates recent research and industry standards, incorporating taxonomies from MITRE, NIST, and OWASP. Next, a dedicated section introduces a secure-by-design AI strategy with threat modeling to demonstrate risk-based defenses and strategies, focusing on integrating MLSecOps and LLMOps into security systems. To gain deeper insights, you’ll cover examples of incorporating CI, MLOps, and security controls, including open-access LLMs and ML SBOMs. Based on the classic NIST pillars, the book provides a blueprint for maturing enterprise AI security, discussing the role of AI security in safety and ethics as part of Trustworthy AI. By the end of this book, you’ll be able to develop, deploy, and secure AI systems effectively.
Table of Contents (27 chapters)
Free Chapter
1
Part 1: Introduction to Adversarial AI
5
Part 2: Model Development Attacks
9
Part 3: Attacks on Deployed AI
14
Part 4: Generative AI and Adversarial Attacks
21
Part 5: Secure-by-Design AI and MLSecOps

Part 1: Introduction to Adversarial AI

In this part, you will get an overview of AI, cybersecurity, and adversarial AI. You will learn the fundamental concepts and terms you need to know to embark on your journey of mastering adversarial AI and AI security. This will cover algorithms, models, model development and deployment, and inference APIs. We will set up our environment and create our first sample AI solution, which we will use later in the book. We will also cover cybersecurity fundaments and how to apply them to our sample solution, including vulnerability and code scanning, while demonstrating our first adversarial attack on our sample AI service.

This part has the following chapters: