GTVS: Boosting the Collection of Application Traffic Ground Truth

Abstract

Interesting research in the areas of traffic classification, network monitoring, and application-oriented analysis can not proceed without real traffic traces, labeled with actual application information. However, hand-labeled traces are an extremely valuable but scarce resource in the traffic monitoring and analysis community, as a result of both privacy concerns and technical difficulties. Hardly any possibility exists for payloaded data to be released, while the impossibility of obtaining certain ground-truth application information from non-payloaded data has severely constrained the value of anonymized public traces.
The usual way to obtain the ground truth is fragile, inefficient and not directly comparable from one’s work to another. This paper proposes a methodology and details the design of a technical framework that significantly boosts the efficiency in compiling the application traffic ground truth. Further, a case study on a 30 minute real data trace is presented. In contrast with past work, this is an easy hands-on tool suite dedicated to save user’s time and labor and is freely available to the public.

Publication
Proceedings of the First International Workshop on Traffic Monitoring and Analysis (TMA’09)
Avatar
Marco Canini
Associate Professor of Computer Science

My current interest is in designing better systems support for AI/ML and provide practical implementations deployable in the real-world.