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.
Al Sadi A., Savi M., Berardi D., Melis A., Prandini M., Callegati F. (2023). Real-time Pipeline Reconfiguration of P4 Programmable Switches to Efficiently Detect and Mitigate DDoS Attacks. Institute of Electrical and Electronics Engineers Inc. [10.1109/ICIN56760.2023.10073501].
Real-time Pipeline Reconfiguration of P4 Programmable Switches to Efficiently Detect and Mitigate DDoS Attacks
Al Sadi A.Primo
Investigation
;Berardi D.Membro del Collaboration Group
;Melis A.Membro del Collaboration Group
;Prandini M.Supervision
;Callegati F.Funding Acquisition
2023
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
