Trojan Code
Adversarial Machine Learning and Secure AI Systems
Buch in deiner Nähe kaufen
Beschreibung
This book provides a comprehensive and accessible guide to the rapidly growing field of AI security, addressing the threats, vulnerabilities, and defensive strategies that shape modern machine-learning systems. The book examines how adversaries exploit poisoned data, hidden triggers, model theft, and privacy leakage to compromise AI, and explains why securing learning systems requires approaches fundamentally different from traditional cybersecurity. Across four structured parts, it maps the threat landscape, dissects backdoor attacks, develops defensive and game-theoretic frameworks, and introduces robust watermarking methods for protecting AI intellectual property.
Drawing from real-world case studies in healthcare, finance, autonomous systems, and defense, the book translates academic research into practical insights for evaluating risk, designing resilient models, and understanding the economic and operational impact of AI breaches. Its coverage extends from adversarial examples and federated learning sabotage to ownership verification and governance-aware design.
Designed for researchers, engineers, graduate students, and institutional decision-makers, this book serves both as a technical reference and a strategic resource for organizations deploying AI in mission-critical environments. It equips readers with the knowledge needed to anticipate emerging threats and to build AI systems that are not only powerful and efficient, but secure, trustworthy, and resilient by design.
This book provides a comprehensive and accessible guide to the rapidly growing field of AI security, addressing the threats, vulnerabilities, and defensive strategies that shape modern machine-learning systems. The book examines how adversaries exploit poisoned data, hidden triggers, model theft, and privacy leakage to compromise AI, and explains why securing learning systems requires approaches fundamentally different from traditional cybersecurity. Across four structured parts, it maps the threat landscape, dissects backdoor attacks, develops defensive and game-theoretic frameworks, and introduces robust watermarking methods for protecting AI intellectual property.
Drawing from real-world case studies in healthcare, finance, autonomous systems, and defense, the book translates academic research into practical insights for evaluating risk, designing resilient models, and understanding the economic and operational impact of AI breaches. Its coverage extends from adversarial examples and federated learning sabotage to ownership verification and governance-aware design.
Designed for researchers, engineers, graduate students, and institutional decision-makers, this book serves both as a technical reference and a strategic resource for organizations deploying AI in mission-critical environments. It equips readers with the knowledge needed to anticipate emerging threats and to build AI systems that are not only powerful and efficient, but secure, trustworthy, and resilient by design.
Offers a complete threat-model view of how modern adversaries manipulate, poison, and compromise AI systems at scale Links AI vulnerabilities to strategic, regulatory, and institutional risks across healthcare, defense, and industry Synthesizes fragmented AI-security research - attacks, defenses, and ownership protection into one unified guide
Autor*in
Kassem Kallas
Themen in »Trojan Code«
Artificial Intelligence Security Adversarial Machine Learning Backdoor Attacks Data Poisoning Model Theft Neural Network Watermarking Intellectual Property Protection for AI Robust Machine Learning AI Trustworthiness Secure AI Systems Model Verification and Validation Adversarial Defense Strategies Cybersecurity for AI AI Governance AI Risk Assessment