Seminar: Adversarial Machine Learning

This seminar is concerned with different aspects of adversarial machine learning. Next to the use of machine learning for security, also the security of machine learning algorithms is essential in practice. For a long time, machine learning has not considered worst-case scenarios and corner cases as those exploited by an adversarial nowadays. The module introduces students to the recently extremely active field of attacks against machine learning and teaches them to work up results from recent research. To this end, the students will read up on a sub-field, prepare a seminar report, and present their work at the end of the term to their colleagues. Topics include but are not limited to adversarial examples, model stealing, membership inferences, poisoning attacks, and defenses against such threats. More information can be found at https://intellisec.de/teaching/aml
Offline

Zusammenfassung

This seminar is concerned with different aspects of adversarial machine learning. Next to the use of machine learning for security, also the security of machine learning algorithms is essential in practice. For a long time, machine learning has not considered worst-case scenarios and corner cases as those exploited by an adversarial nowadays.

The module introduces students to the recently extremely active field of attacks against machine learning and teaches them to work up results from recent research. To this end, the students will read up on a sub-field, prepare a seminar report, and present their work at the end of the term to their colleagues.

Topics include but are not limited to adversarial examples, model stealing, membership inferences, poisoning attacks, and defenses against such threats.


More information can be found at https://intellisec.de/teaching/aml

Allgemein

Sprache
Deutsch
Copyright
This work has all rights reserved by the owner.

Verfügbarkeit

Zugriff
1. Sep 2021, 18:00 - 1. Mär 2022, 17:00
Aufnahmeverfahren
Sie können diesem Kurs direkt beitreten.
Zeitraum für Beitritte
Bis: 8. Nov 2021, 23:55
Spätester Kursaustritt
4. Nov 2021
Veranstaltungszeitraum
19. Okt 2021 - 11. Feb 2022

Für Kursadministratoren freigegebene Daten

Daten des Persönlichen Profils
Anmeldename
Vorname
Nachname
E-Mail
Matrikelnummer

Zusätzliche Informationen

Objekt-ID
2147168