Presentation Information
[MG1-3]Assessing the Robustness of In-Switch Neural Networks Against Adversarial DDoS Attacks
○Giulio Zingrillo1,2,3, Emilio Paolini1, Nicola Andriolli3, Francesco Paolucci2, Filippo Cugini2, Giampiero Contestabile1, Piero Castoldi1, Lorenzo De Marinis1 (1.Scuola Superiore Sant'Anna, 2.CNIT - National Inter-University Consortium for Telecommunications, 3.University of Pisa)
Keywords:
Converged mobile and optical access networks,Fog/edge computing infrastructure and applications,Network function virtualization (NFV)
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 white-box and black-box adversarial attacks.