Humboldt-Universität zu Berlin - Mathematisch-Naturwissenschaftliche Fakultät - Institut für Informatik

Verteidigung Masterarbeit: Jan Schröder

"Risk assessment in Machine Learning security - a framework for risk measurement"

Die Verteidigung findet digital per Zoom statt. Eine Zoom-Einladung finden Sie hier. (nur mit Informatik-Account)

Abstract:

This thesis deals with the field of machine learning, especially security. For this purpose, the concept of a technical framework will be described, implemented and evaluated in a case study. Based on ISO 27004, risk indicators are used to measure and evaluate the extent of damage and the effort required by an attacker. It is not possible, as assumed, to determine a risk value that represents the extent of the damage and the effort. Therefore, four different risk matrices will represent different values and must be interpreted individually. This thesis can be found together with the Risk-Measurement-Framework on https://github.com/EvilWatermelon/Risk-Measurement-Framework.