University · Artificial Intelligence · AI Ethics, Safety, and Alignment
Adversarial Machine Learning: Attacks, Defences, and Robustness
4 Abschnitte
Adversarial examples (FGSM, PGD, CW attacks), evasion vs poisoning vs backdoor attacks, certified robustness via randomised smoothing, adversarial training as defence, robustness–accuracy trade-offs, and implications for safety-critical AI deployment.
Inhaltsübersicht
- Adversarial Examples: Discovery, Anatomy, and Attack Methods
- Beyond Evasion: Poisoning, Backdoor, and Physical-World Attacks
- Defences: Adversarial Training and Certified Robustness
- Robustness–Accuracy Trade-offs, Ethical Dimensions, and Open Problems
📚 Vollständiges Lernmaterial mit 4 Abschnitten, Karteikarten und Quizzen verfügbar nach Anmeldung.
Jetzt kostenlos lernen →Related Topics
Interaktiv lernen mit Karteikarten & Quizzen
Melde dich an und lerne AI Ethics, Safety, and Alignment mit intelligenten Wiederholungen, Quizzen und KI-Lernhilfen. 7 Tage kostenlos.
Kostenlos testen