Kolloquiumsvortrag 11. November 2025, Wladimir Urban (Betreuer: Al Sardy/Muhammad)
A framework for preparing and assessing cybersecurity datasets
Cyber-physical security research relies on datasets that are trustworthy, well-documented, and temporally coherent. In practice, many public datasets often show weak documentation, inconsistent or missing labels, unstable feature definitions, class imbalance, temporal drift, and other obstacles that can inflate reported performance and undermine external validity. Existing tools are fragmented, rarely support end-to-end reproducibility, and are not tailored to cybersecurity datasets, particularly in smart-grid contexts.
This thesis aims to develop an integrated framework (A.R.C.) for standardized dataset preparation and assessment in cybersecurity research. And to evaluate whether such standardization can improve detection performance and computational efficiency, while strengthening the reliability and comparability of findings.
Zeit: 10:15 Uhr
Ort: Raum 04.137, Martensstr. 3, Erlangen
Zoom-Meeting :
https://fau.zoom-x.de/j/68350702053?pwd=UkF3aXY0QUdjeSsyR0tyRWtLQ0hYUT09
Meeting-ID: 683 5070 2053
Kenncode: 647333