paper-with-me

Papers

TrafficMoE: Heterogeneity-aware Mixture of Experts for Encrypted Traffic Classification

2026-03-31 · Qing He, Xiaowei Fu, Lei Zhang arxiv

Encrypted traffic classification is a critical task for network security. While deep learning has advanced this field, the occlusion of payload semantics by encryption severely challenges standard modeling approaches. Most existing frameworks rely on static and homogeneous pipelines that apply uniform parameter sharing and static fusion strategies across all inputs. This one-size-fits-all static design is inherently flawed: by forcing structured headers and randomized payloads into a unified processing pipeline, it inevitably entangles the raw protocol signals with stochastic encryption noise, thereby degrading the fine-grained discriminative features. In this paper, we propose TrafficMoE, a framework that breaks through the bottleneck of static modeling by establishing a Disentangle-Filter-Aggregate (DFA) paradigm. Specifically, to resolve the structural between-components conflict, the architecture disentangles headers and payloads using dual-branch sparse Mixture-of-Experts (MoE), enabling modality-specific modeling. To mitigate the impact of stochastic noise, an uncertainty-aware filtering mechanism is introduced to quantify reliability and selectively suppress high-variance representations. Finally, to overcome the limitations of static fusion, a routing-guided strategy aggregates cross-modality features dynamically, that adaptively weighs contributions based on traffic context. With this DFA paradigm, TrafficMoE maximizes representational efficiency by focusing solely on the most discriminative traffic features. Extensive experiments on six datasets demonstrate TrafficMoE consistently outperforms state-of-the-art methods, validating the necessity of heterogeneity-aware modeling in encrypted traffic analysis. The source code is publicly available at https://github.com/Posuly/TrafficMoE_main.

📄 PDF Abstract BibTeX arXiv:2603.29520

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2024-11-20 · Yuxuan Chen, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

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 para…

DecoderLanguage ModelingLanguage ModellingLarge Language Model+2

MalMoE: Mixture-of-Experts Enhanced Encrypted Malicious Traffic Detection Under Graph Drift

2026-02-10 · Yunpeng Tan, Qingyang Li, Mingxin Yang, Yannan Hu 외 arxiv

Encryption has been commonly used in network traffic to secure transmission, but it also brings challenges for malicious traffic detection, due to the invisibility of the packet payload. Graph-based methods are emerging …

Data Augmentation

HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs

2025-04-04 · Yongji Wu, Xueshen Liu, Shuowei Jin, Ceyu Xu 외

The Mixture-of-Experts (MoE) architecture has become increasingly popular as a method to scale up large language models (LLMs). To save costs, heterogeneity-aware training solutions have been proposed to utilize GPU clus…

GPUMixture-of-Experts

HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecasting

2024-11-30 · Shaohan Yu, Pan Deng, Yu Zhao, Junting Liu 외

Achieving both accurate and consistent predictive performance across spatial nodes is crucial for ensuring the validity and reliability of outcomes in fair spatial-temporal forecasting tasks. However, existing training m…

FairnessMixture-of-ExpertsPrediction

GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts

2024-12-15 · Zihao Guo, Qingyun Sun, Haonan Yuan, Xingcheng Fu 외

Real-world graphs have inherently complex and diverse topological patterns, known as topological heterogeneity. Most existing works learn graph representation in a single constant curvature space that is insufficient to …