Vortrag von Samuel Kopmann, Karlsruhe Institute of Technology KIT

16. September 2025
Title: Feedback-driven Autonomous Data Set Labeling for Denial-of-Service Attack Traffic

Datum: 16.09.2025
Uhrzeit: 12:00 p.m.
Raum: CG0118

Abstract: Expert-driven labeling of network traffic for Denial of Service (DoS) detection is error prone and prohibitively expensive in large-scale environments, such as Internet Service Provider (ISP) networks. However, supervised Machine Learning-based (ML) DoS detection approaches require high-quality and up-to-date training data sets. To ensure fast and high-quality data set creation for ML model training while facing evolving traffic patterns in the legitimate and the attack traffic, there is a need for a
labeling approach without an expert in the loop. This presentation outlines FeADable, a retrospective and fully autonomous labeling approach that leverages autoencoders to distinguish between legitimate and attack traffic based on reported feedback about occurred attacks. FeADable enables the scalable labeling of application layer DoS attacks and volumetric Distributed DoS (DDoS) attacks with near-perfect precision and false-positive feedback resilience, which ensures fast retraining of deployed detection models in response to successful attacks. The presentation covers evaluation results of FeADable with authentic, real-world data sets that are publicly available, i.e., from the Canadian Institute for Cybersecurity, and with network traffic of a tier-1 ISP. I will further outline FeADable’s compatibility with different monitoring approaches, i.e., micro-flows and traffic aggregates, to emphasize its labeling capability of DoS traffic independent of the traffic representation.

Samuel Kopmann has been working as a Research Assistant and Ph.D. candidate at the Institute of Telematics, Karlsruhe Institute of Technology since 2021.

He is interested in the application of computer vision approaches to network traffic classification and developing novel approaches to overcome limited data availability for Machine Learning (ML) in networking. His research focuses on detecting and mitigating volumetric DDoS attacks with ML while maintaining fixed and predictable resource consumption, i.e., memory and CPU utilization.