Assessing the Robustness of In-Switch Neural Networks Against Adversarial DDoS Attacks
In data-plane deployment of DNNs allows for improved edge functionality and intrusion detection. We report on the increased resilience of in-switch LUT-distilled neural networks to whitebox and black-box adversarial attacks.
Authors
- Nicola Andriolli (ORCID: https://orcid.org/0000-0001-8322-6854)
- G. Contestabile (ORCID: https://orcid.org/0000-0001-8703-3291)
- Filippo Cugini (ORCID: https://orcid.org/0000-0002-9840-0365)
- Lorenzo De Marinis (ORCID: https://orcid.org/0000-0003-1462-3199)
- Emilio Paolini (ORCID: https://orcid.org/0000-0001-7486-9268)
- P. Castoldi (ORCID: https://orcid.org/0000-0003-4366-0730)
- Francesco Paolucci
- Giulio Zingrillo
Institutions
- University of Pisa (IT)
- Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT)
- Scuola Superiore Sant'Anna (IT)
- Consorzio Nazionale Interuniversitario per le Telecomunicazioni (IT)
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11111457
- Primary Topic
- Network Security and Intrusion Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission