Saved in:
Bibliographic Details
Main Authors: Zhou, Jiajun, Sun, Changhui, Shen, Meng, Yu, Shanqing, Xuan, Qi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.00357
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917179953250304
author Zhou, Jiajun
Sun, Changhui
Shen, Meng
Yu, Shanqing
Xuan, Qi
author_facet Zhou, Jiajun
Sun, Changhui
Shen, Meng
Yu, Shanqing
Xuan, Qi
contents While pre-trained large models have achieved state-of-the-art performance in network traffic analysis, their prohibitive computational costs hinder deployment in real-time, throughput-sensitive network defense environments. This work bridges the gap between advanced representation learning and practical network protection by introducing Traffic-MoE, a sparse foundation model optimized for high-efficiency real-time inference. By dynamically routing traffic tokens to a small subset of specialized experts, Traffic-MoE effectively decouples model capacity from computational overhead. Extensive evaluations across three security-oriented tasks demonstrate that Traffic-MoE achieves up to a 12.38% improvement in detection performance compared to leading dense competitors. Crucially, it delivers a 91.62% increase in throughput, reduces inference latency by 47.81%, and cuts peak GPU memory consumption by 38.72%. Beyond efficiency, Traffic-MoE exhibits superior robustness against adversarial traffic shaping and maintains high detection efficacy in few-shot scenarios, establishing a new paradigm for scalable and resilient network traffic analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00357
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Traffic-MoE: A Sparse Foundation Model for Network Traffic Analysis
Zhou, Jiajun
Sun, Changhui
Shen, Meng
Yu, Shanqing
Xuan, Qi
Cryptography and Security
While pre-trained large models have achieved state-of-the-art performance in network traffic analysis, their prohibitive computational costs hinder deployment in real-time, throughput-sensitive network defense environments. This work bridges the gap between advanced representation learning and practical network protection by introducing Traffic-MoE, a sparse foundation model optimized for high-efficiency real-time inference. By dynamically routing traffic tokens to a small subset of specialized experts, Traffic-MoE effectively decouples model capacity from computational overhead. Extensive evaluations across three security-oriented tasks demonstrate that Traffic-MoE achieves up to a 12.38% improvement in detection performance compared to leading dense competitors. Crucially, it delivers a 91.62% increase in throughput, reduces inference latency by 47.81%, and cuts peak GPU memory consumption by 38.72%. Beyond efficiency, Traffic-MoE exhibits superior robustness against adversarial traffic shaping and maintains high detection efficacy in few-shot scenarios, establishing a new paradigm for scalable and resilient network traffic analysis.
title Traffic-MoE: A Sparse Foundation Model for Network Traffic Analysis
topic Cryptography and Security
url https://arxiv.org/abs/2601.00357