The AI Security Handbook
No Starch Press,US (Verlag)
978-1-7185-0466-0 (ISBN)
- Noch nicht erschienen (ca. Juni 2026)
- Versandkostenfrei
- Auch auf Rechnung
- Artikel merken
As AI technologies become increasingly popular, bad actors have begun targeting them for disruption. This book introduces you to the burgeoning fields of machine learning hacking and AI security.
You’ll follow simple examples written in the Python programming language to learn about training and deploying a machine learning model, then dive into the cyberattacks that can force those models to malfunction, whether by disclosing sensitive information or incorrectly classifying a result, sometimes with devastating outcomes.
Once you gain experience performing these attacks yourself, you’ll explore the ecosystem of tools that exist to defend against them before touring the ways the industry tries to secure AI by assessing risk, implementing standards, and influencing legislation.
Uses Python 3
Harriet Farlow is the CEO and Founder of AI security company, Mileva Security Labs. Her PhD is in adversarial machine learning, and she holds a Masters in Cyber Security and a Bachelor in Physics and Biological Anthropology. She has spent ten years working at the intersection of AI and security, as a Senior Consultant at Deloitte Australia, a data scientist at Sydney University, Senior Delivery Lead at New York-based start-up Decoded, and as acting Technical Director at the Australian Signals Directorate’s AI Hub. She now runs Mileva Security Labs, which provides AI assessment, advisory and training. As a previous DEF CON speaker she is also passionate about educating on AI security issues through her youtube channel HarrietHacks and as the host of The AI Security Podcast.
Foreword
Acknowledgments
Introduction
Part I: AI and Security Fundamentals
Chapter 1: What Is AI?
Chapter 2: Working with models
Chapter 3: The Threat Landscape
Part II: Attacking and Defending AI
Chapter 4: Attacks and Weaknesses
Chapter 5: Defenses, Controls, and Mitigations
Part III: The AI Security Ecosystem
Chapter 6: Red Teaming AI
Chapter 7: Attacking and Defending with AI
Chapter 8: Safety
Chapter 9: Governance
Chapter 10: What's Next for AI Security
Conclusion: A New Kind of Hacker
Index
| Erscheint lt. Verlag | 9.6.2026 |
|---|---|
| Verlagsort | San Francisco |
| Sprache | englisch |
| Maße | 178 x 235 mm |
| Gewicht | 369 g |
| Themenwelt | Mathematik / Informatik ► Informatik ► Programmiersprachen / -werkzeuge |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| ISBN-10 | 1-7185-0466-7 / 1718504667 |
| ISBN-13 | 978-1-7185-0466-0 / 9781718504660 |
| Zustand | Neuware |
| Informationen gemäß Produktsicherheitsverordnung (GPSR) | |
| Haben Sie eine Frage zum Produkt? |
aus dem Bereich
