Buch, Englisch, 432 Seiten, Format (B × H): 178 mm x 254 mm
An Integrated Introduction
Buch, Englisch, 432 Seiten, Format (B × H): 178 mm x 254 mm
ISBN: 978-1-032-48275-0
Verlag: Taylor & Francis Ltd
Machine learning is now used throughout cybersecurity, from phishing and malware detection to intrusion analysis, fraud detection, and security automation. At the same time, machine-learning systems have become targets themselves: their data may be noisy or manipulated, their operating environment may change, and adversaries may attack models, prompts, retrieval pipelines, and deployed AI applications.
AI for Security and Security for AI develops these two perspectives together. Rather than treating benchmark accuracy as sufficient, the book emphasizes data quality, defensible experimental design, rare-event evaluation, changing threats, and explicit adversarial threat models. Classical analytics and strong baselines are connected to deep learning, transformers, low-resource learning, continual learning, and adversarial machine learning.
Key Features:
• Security case studies span phishing, malware, intrusion detection, fraud, and text-based threats.
• Examples emphasize realistic train/test separation, leakage control, prevalence, and operational error costs.
• Modern methods are compared with simpler baselines so added model complexity can be evaluated rather than assumed beneficial.
• Exercises and practitioner-oriented examples connect mathematical ideas to reproducible security experiments.
The book is intended for advanced undergraduate and graduate courses in cybersecurity, security analytics, machine learning, and applied AI, as well as for researchers and practitioners who need to build, evaluate, or audit learning systems operating in adversarial and changing environments.
Zielgruppe
Postgraduate and Undergraduate Advanced
Autoren/Hrsg.
Weitere Infos & Material
1. Introduction 2. Data Quality for Security 3. Imbalanced Learning for Security 4. Deep Learning for Security 5. Low-Resource Learning 6. Lifelong Learning 7. Adversarial ML 8. Summary




