Not with a bug but with a sticker
attacks on machine learning systems and what to do about them
Bibliographic details
Additional authors
Anderson, Hyrum Kumar, Siva
Summary
This book provides an accessible yet comprehensive introduction to the security risks facing modern artificial intelligence and machine learning systems. The authors explain how adversaries exploit weaknesses through techniques such as adversarial examples, data poisoning, model evasion, and manipulation of training data. Using case studies from industry, government, and academic research, the book illustrates the real-world consequences of insecure AI systems and outlines strategies for defense and risk mitigation. Intended for machine learning engineers, cybersecurity professionals, policymakers, and researchers, it highlights the importance of securing AI technologies in an increasingly AI-driven world.