Skip to main navigation Skip to search Skip to main content

HALIDS: a Hardware-Assisted Machine Learning IDS for in-Network Monitoring

  • Belén Brandino
  • , Eduardo Grampin
  • , Katharina Dietz
  • , Nikolas Wehner
  • , Michael Seufert
  • , Tobias Hoßfeld
  • , Pedro Casas-Hernandez (Author and Speaker)
  • Universidad de la República
  • University of Würzburg
  • Augsburg University

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Poster Presentation › peer-review

Abstract

Early decision-making at the network device level is crucial for network security. This entails moving beyond traditional forwarding functions towards more intelligent network devices. Integrating Machine Learning (ML) models into the data plane enables quicker processing and reduced reliance on the control plane. This paper explores the development of a ML-driven Intrusion Detection System (IDS) where network devices autonomously make security decisions or defer to an expert Oracle, relying on in-band and off-band traffic analysis. Programmable devices, such as those using P4, are essential to enable these functionalities and allow for network device re-training to adapt to changing traffic patterns. We introduce HALIDS, a prototype for in-band ML-IDS using P4, complemented with off-band Oracles which support in-network ML-driven classification with more confident classifications, targeting an active learning logic for more accurate in-band analysis. We implement HALIDS using the open source software switch BMv2, and show its operation with real traffic traces publicly available.
Original languageEnglish
Title of host publication2024 8th Network Traffic Measurement and Analysis Conference (TMA)
Pages1-4
Number of pages4
ISBN (Electronic)978-3-903176-64-5
DOIs
Publication statusPublished - 20 Jun 2024
Event2024 8th Network Traffic Measurement and Analysis Conference (TMA) - Dresden, Dresden, Germany
Duration: 21 May 2024 → 24 May 2024

Conference

Conference2024 8th Network Traffic Measurement and Analysis Conference (TMA)
Country/TerritoryGermany
CityDresden
Period21/05/24 → 24/05/24

Research Field

  • Multimodal Analytics

Fingerprint

Dive into the research topics of 'HALIDS: a Hardware-Assisted Machine Learning IDS for in-Network Monitoring'. Together they form a unique fingerprint.

Cite this