Our student Jan Svoboda participated with a poster presentation in the 30th International Student Scientific Conference, POSTER 2026. This annual international conference that takes place in Prague, is an excellent opportunity to network among international doctoral and master students. Often the first opportunity to present their research and gain experience in science communication.
Poster: Multi-Objective Model Selection Pipeline for Network Flow Classification
Abstract: Training classifiers for network intrusion detection is hindered by two types of problems: data challenges (lack of labels, class imbalance, non-IID data, and concept drift) and engineering challenges (memory & compute efficiency, data ingestion, parallel training, and hyperparameter optimization). Existing ad-hoc scripts make it hard to reproduce results or compare models systematically across these conditions. An extendable machine learning pipeline is developed to address both, targeting malicious network flow classifiers for the Stratosphere Linux IPS (Slips). The output is a set of best-performing models at different FPR and F1 thresholds suitable for deployment in Slips.
Implementation: https://github.com/stratosphereips/Slips-ML-Training-Pipeline
