In this work we demonstrate the integration of P4 enabled switches with high level AI techniques with the aim to improve efficiency and performance of DDoS detection and mitigation. Powerful ML-based strategies are adopted only when a suspicious behaviour is occurring in the network, and its activation is triggered by a coarser-grained and lightweight strategy fully executable in the data plane.

Real-time Pipeline Reconfiguration of P4 Programmable Switches to Efficiently Detect and Mitigate DDoS Attacks

Berardi D.;
2023-01-01

Abstract

In this work we demonstrate the integration of P4 enabled switches with high level AI techniques with the aim to improve efficiency and performance of DDoS detection and mitigation. Powerful ML-based strategies are adopted only when a suspicious behaviour is occurring in the network, and its activation is triggered by a coarser-grained and lightweight strategy fully executable in the data plane.
2023
979-8-3503-9804-5
P4 DDoS detection Machine Learning Programmable Data Plane
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12606/10308
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
social impact