MERLOT combines distilled GPT-2 experts with a one-hot gating network to classify encrypted traffic directly from the final decoder token, reporting competitive F1 scores at a fraction of TrafficLLM's resource cost.
ET-BERT: A contextualized datagram rep- resentation with pre-training transformers for encrypted traffic classifi- cation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification
MERLOT combines distilled GPT-2 experts with a one-hot gating network to classify encrypted traffic directly from the final decoder token, reporting competitive F1 scores at a fraction of TrafficLLM's resource cost.