DDoS Mitigation at Line Rate—With P4 and LUTs
Detecting DDoS attacks at wirespeed requires in-network AI. Our P4 LUT distillation deploys a DNN-based…
ByPhilip
Lossless DNN Distillation for P4 Hardware
Traditional DNN quantization sacrifices accuracy—our LUT-based distillation doesn’t. By mapping neurons to flow tables, we…
Deploying DNNs in P4 Switches—Without ALUs
Hardware P4 switches lack ALUs and fast stateful memory, making DNN deployment impossible—until now. Our…
Edge vs. Cloud: Where Should B5G AI/ML Models Retrain?
Retraining at the edge reduces latency but limits computational power; retraining in the cloud offers…