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.
Universal embedding function for traffic classification via quic domain recognition pretraining: A transfer learning success,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.