Lehrstuhl für Informatik III
Some of my research interests include the following:
- Everything related to network management, e.g., performance prediction or anomaly detection
- Machine Learning (ML) in communication networks, including but not limited to
- Data synthetization via Generative Adversarial Networks (GANs)
- Transfer Learning mechanisms
- Active Learning mechanisms
- Uncertainty in ML
- Network simulation with OMNeT++ and other tools
- Statistics evaluation and ML in R and Python
Open theses can be found here. Note that a lot of these topics can be tailored to either bachelor theses, master theses or student projects.
Dietz, K., Gray, N., Seufert, M., & Hoßfeld, T. ML-based Performance Prediction of SDN using Simulated Data from Real and Synthetic Networks. 33th IEEE IFIP Network Operations and Management Symposium (NOMS).
Dietz, K., Mühlhauser, M., Seufert, M., Gray, N., Hoßfeld, T., & Herrmann, D. Browser Fingerprinting: How to Protect Machine Learning Models and Data with Differential Privacy?. 1st International Workshop on Machine Learning in Networking (MaLeNe).
Gray, N., Dietz, K., Seufert, M., & Hoßfeld, T. High Performance Network Metadata Extraction Using P4 for ML-Based Intrusion Detection Systems. 22nd International Conference on High Performance Switching and Routing (HPSR).
Dietz, K. Identification and Evaluation of KPIs in SDN via Simulation for Establishing Topology Classifications and Prediction Models [Master thesis]. University of Würzburg.
Gray, N., Dietz, K., & Hoßfeld, T. Simulative Evaluation of KPIs in SDN for Topology Classification and Performance Prediction Models. 2020 16th International Conference on Network and Service Management (CNSM).
Dietz, K. Extending the OpenFlow OMNeT++ Suite [Master thesis]. University of Würzburg.