David J. Miller (Pennsylvania State University), Zhen Xiang (Urbana-Champaign University of Illinois), George Kesidis (Pennsylvania State University)

Adversarial Learning and Secure AI

• Gebundenes Buch

Produktbeschreibung

Designed for upper undergraduate and graduate courses on adversarial learning and AI security, this textbook connects theory with practice using real-world examples, case studies, and hands-on student projects.

---

Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.

Produktdetails

• Verlag: Cambridge University Press
• Seitenzahl: 350
• Erscheinungstermin: 31. August 2023
• Englisch
• Abmessung: 175mm x 251mm x 25mm
• Gewicht: 866g
• ISBN-13: 9781009315678
• ISBN-10: 1009315676
• Artikelnr.: 67823528

Autorenporträt

David J. Miller is Professor of Electrical Engineering at the Pennsylvania State University.

Inhaltsangabe

Contents
Preface
Notation
1. Overview of adversarial learning
2. Deep learning background
3. Basics of detection and mixture models
4. Test-time evasion attacks (adversarial inputs)
5. Backdoors and before/during training defenses
6. Post-training reverse-engineering defense (PT-RED) Against Imperceptible Backdoors
7. Post-training reverse-engineering defense (PT-RED) against patch-incorporated backdoors
8. Transfer post-training reverse-engineering defense (T-PT-RED) against backdoors
9. Universal post-training backdoor defenses
10. Test-time detection of backdoor triggers
11. Backdoors for 3D point cloud (PC) classifiers
12. Robust deep regression and active learning
13. Error generic data poisoning defense
14. Reverse-engineering attacks (REAs) on classifiers
Appendix. Support Vector Machines (SVMs)
References
Index.