FlowCLIP applies contrastive pretraining with domain-name text supervision to learn transferable representations from QUIC traffic side-channel features, matching supervised performance on time-split evaluation.
A survey on encrypted network traffic analysis applications, techniques, and countermeasures
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.NI 2verdicts
UNVERDICTED 2representative citing papers
netFound is a pretrained network foundation model using protocol-aware tokenization, context embedding, hierarchical attention, and privacy design that reaches F1 0.95 on exogenous context discrimination versus under 0.62 for prior models.
citing papers explorer
-
FlowCLIP: Contrastive Pretraining Using Domain Names for Encrypted Traffic Classification
FlowCLIP applies contrastive pretraining with domain-name text supervision to learn transferable representations from QUIC traffic side-channel features, matching supervised performance on time-split evaluation.
-
netFound: Principled Design for Network Foundation Models
netFound is a pretrained network foundation model using protocol-aware tokenization, context embedding, hierarchical attention, and privacy design that reaches F1 0.95 on exogenous context discrimination versus under 0.62 for prior models.