mlsanityData to 14 Oct 2026

MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification

arXiv 2411.13004 ↗First posted 20 Nov 2024cs.LG cs.CRcited by 1

On the map: Mixture-of-experts → Expert routing strategies

Abstract (arXiv)

We present MERLOT, a scalable mixture-of-expert (MoE) based refinement of distilled large language model optimized for encrypted traffic classification. By applying model distillation techniques in a teacher-student paradigm, compact models derived from GPT-2-base retain high classification accuracy while minimizing computational costs. These models function as specialized experts in an MoE architecture, dynamically assigned via a gating network. Unlike generation-based methods, our approach directly classifies encrypted traffic using the final decoder token with contextual feature embedding as input. Experiments on 10 datasets show superior or competitive performance over the state-of-the-art models while significantly reducing resource demands, underscoring its effectiveness and robustness.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts. Builds on 11 of its 22 references that are in the map. First posted on arXiv 20 Nov 2024.

Builds on

11 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Harder Tasks Need More Experts: Dynamic Routing in MoE Models12 Mar
  2. 2022Mixture-of-Experts with Expert Choice Routing18 Feb

Other references · 9

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2024NetLLM: Adapting Large Language Models for Networkingcited by 78
  5. 2017Deep Packet: A Novel Approach For Encrypted Traffic Classification Using Deep Learningcited by 70
  6. 2022ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classificationcited by 66
  7. 2023NetGPT: Generative Pretrained Transformer for Network Trafficcited by 31
  8. 2021Deep Learning and Traffic Classification: Lessons learned from a commercial-grade dataset with hundreds of encrypted and zero-day applicationscited by 14
  9. 2023Generative Adversarial Classification Network with Application to Network Traffic Classificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Unknown-Traffic Detection, Calibration and Shortcut Reliance in Distilled Encrypted-Traffic Classifiers over One Yearcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026TrafficMoE: Heterogeneity-aware Mixture of Experts for Encrypted Traffic Classification
  2. 2026TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
  3. 2026Treat Traffic Like Trees: A Semantic-Preserving Hierarchical Graph-Based Expert Framework for Encrypted Traffic Analysis
  4. 2026Pruned Traffic Trees: Native Semantic Compression with a Protocol-Structured Model Family for Encrypted Traffic Classification
  5. 2026MalMoE: Mixture-of-Experts Enhanced Encrypted Malicious Traffic Detection Under Graph Drift
  6. 2026Mean Masked Autoencoder with Flow-Mixing for Encrypted Traffic Classification
  7. 2026Multimodal Reasoning with LLM for Encrypted Traffic Interpretation: A Benchmark
  8. 2026NetMamba+: A Framework of Pre-trained Models for Efficient and Accurate Network Traffic Classification