Trojan Code: Adversarial Machine Learning and Secure AI Systems

Erscheinungsjahr 2026
ISBN: 978-3-032-24521-2
Verlag: Springer Nature Switzerland AG

Buch, Englisch, 358 Seiten, Format (B × H): 155 mm x 235 mm

 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.

Zielgruppe

Research

Autoren/Hrsg.

Kallas, Kassem

Fachgebiete

• Mathematik | Informatik EDV | Informatik EDV & Informatik Allgemein Rechtliche Aspekte der EDV
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Technische Informatik Computersicherheit

Inhaltsverzeichnis

Chapter 1 Introduction.- Part I Foundations of Artificial Intelligence Security.- Chapter 2 Mapping the AI-Security Battlefield: Threats Across the
Machine-Learning Lifecycle.- Chapter 3 Behind the Backdoors: Threats and Safeguards for Deep-Learning Systems.- Part II Backdoor Attacks and Defenses in Deep Neural Networks.- Chapter 4 Stealthy Clean-Label Backdoors: How an Image-Classification Model Can Be Attacked.- Chapter 5 Illumination-Modulated Video Backdoor Attacks on Anti-Spoofing Rebroadcast Detectors.- Chapter 6 Power Play: Backdooring DNNs Through Energy-Drain Triggers.- Chapter 7 Expecting the Next Move: Robust Backdoors under Non-IID Federated Training.- Chapter 8 When One Shield Is Not Enough: Layering Defenses Against Backdoor Attacks.- Chapter 9 Rare-Event Simulation for Black-Box Backdoor Defense.- Chapter 10 Game-Theoretic Modeling of BackdoorAttacker–Defender Dynamics.- Chapter 11 Cost-Constrained Backdoor Games in Deep Learning.- Part III DNN Watermarking for Intellectual Property Protection.- Chapter 12 Robust and Secure Watermarking for Deep Neural Networks.- Chapter 13 DNN Watermarking in Blackbox Settings using Image Mixup.- Chapter 14 Cryptographically Bound Mixup Watermarks for Black-Box DNNs.- Part IV Emerging Trends, Open Issues, and Future Research Directions in AI Security.- Chapter 15 Security Horizons: Emerging Threats and Future Directions for Trustworthy AI.- Index.

Über Autor(innen)

Kassem Kallas, Ph.D., HDR, EMBA, Senior Member IEEE , is a Senior Scientist at the French National Institute of Health and Medical Research (INSERM) and a Professor in collaboration with IMT Atlantique. He is internationally recognized for his contributions to Artificial Intelligence Security, Cybersecurity, and Adversarial Machine Learning, with impactful work spanning Europe, the United States, and the Middle East.

Dr. Kallas earned his Ph.D. in Information Engineering and Science from the University of Siena (Italy), where he developed a  . This foundational work influenced research in wireless sensor networks, cognitive radio systems, image forensics, and adversarial learning. In 2025, he completed the  Habilitation à Diriger des Recherches (HDR)  at the University of Western Brittany (UBO), the highest academic qualification in the French university system.

His international career includes positions at prestigious institutions. From 2020 to 2022, he served as a Research Fellow at the  U.S. National Institute of Standards and Technology (NIST) , contributing to wireless communication and signal analysis research. He then joined  Inria France , where he worked on the  SAIDA  project focused on securing AI systems for defense applications. He currently serves at INSERM, where he conducts research on the security and privacy of AI for healthcare applications and supervises doctoral work in these areas.

Dr. Kallas contributes to several major French national research initiatives, including the PEPR  “Secure, Safe, and Fair Machine Learning for Digital Health (SSF-ML-DH)” , and the  CybAille Industrial Chair in Cybersecurity and Trustworthy AI for Health , which bring together partners such as IMT Atlantique, Université PSL, CEA-LIST, Thales, and CHU Brest.