A contrastive learning transformer embeds network flow sequences to enable correlation clustering that groups scanner sources consistently with labels.
Waiting for quic: Passive measurements to understand quic deployments,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
FlowCLIP pretrains a traffic encoder via CLIP-style contrastive loss on domain names from side-channel features, then freezes it for linear probing classification that outperforms baselines on later weeks of QUIC traffic.
citing papers explorer
-
FlowCLIP: Contrastive Pretraining Using Domain Names for Encrypted Traffic Classification
FlowCLIP pretrains a traffic encoder via CLIP-style contrastive loss on domain names from side-channel features, then freezes it for linear probing classification that outperforms baselines on later weeks of QUIC traffic.