paper-with-me

Papers

Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC

2025-08-04 · Chungang Lin, Xuying Meng, Tianyu Zuo, Weiyao Zhang, Meng Shen, Ruijie Zhao, Guanming Che, Ruiqi Meng, Ziyue Huang, Haitong Luo, Zhiwei Xu, Yujun Zhang arxiv

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and further vulnerabilities. These pressures have produced two disjoint research lines: 1) versatile analysis, via network foundation models for low label dependency, and 2) efficient analysis, via hardware offloading for low analysis latency. However, versatility and efficiency have appeared fundamentally incompatible to co-achieve, with prior work consistently sacrificing one for the other, yet we show that this incompatibility is a consequence of polarized design choices across the three components of traffic analysis systems, i.e., traffic processing, model architecture, and analysis execution. In response, we present Nepco, a versatile yet efficient network traffic analysis system that offloads network foundation models to SmartNIC. Our key observation is that discriminative traffic information is concentrated in localized byte regions, motivating versatile yet efficient localized byte-sequence modeling rather than inefficient global modeling. To exploit this without incurring the latency bottlenecks of complex encoding steps, we employ a hardware-friendly processing pipeline that directly embeds raw byte sequences. Crucially, to maintain versatility across diverse tasks, we propose a pattern-aware convolutional architecture equipped with dedicated scoring and gating mechanisms. By exploiting translation invariance, this design dynamically locates and extracts salient semantic signatures. We prototype Nepco on the Nvidia BlueField-3 SmartNIC with multiengine collaborative analysis execution. The experimental results demonstrate that Nepco achieves macro F1 competitive with the best performances achieved by 8 state-of-the-art network foundation models, while reducing end-to-end latency by 328x to the millisecond scale.

📄 PDF Abstract BibTeX arXiv:2508.02001

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cora: Accelerating Stateful Network Applications with SmartNICs

2024-10-29 · Shaoke Xi, Jiaqi Gao, Mengqi Liu, Jiamin Cao 외

With the growing performance requirements on networked applications, there is a new trend of offloading stateful network applications to SmartNICs to improve performance and reduce the total cost of ownership. However, o…

CPU

Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks

2022-12-05 · Yeguang Qin, Yilin Yang, Fengxiao Tang, Xin Yao 외

The Space-Air-Ground Integrated Network (SAGIN) plays a pivotal role as a comprehensive foundational network communication infrastructure, presenting opportunities for highly efficient global data transmission. Nonethele…

FairnessFederated Learningreinforcement-learningReinforcement Learning+1

ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching

2025-09-21 · Xingyu Xiang, Raj Joshi, Yuhan Liu, Jiayi Yao 외 arxiv

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mi…

GPUs, CPUs, and... NICs: Rethinking the Network's Role in Serving Complex AI Pipelines

2025-01-22 · Mike Wong, Ulysses Butler, Emma Farkash, Praveen Tammana 외

The increasing prominence of AI necessitates the deployment of inference platforms for efficient and effective management of AI pipelines and compute resources. As these pipelines grow in complexity, the demand for distr…

Management

Cellular traffic offloading via Opportunistic Networking with Reinforcement Learning

2021-10-01 · Lorenzo Valerio, Raffaele Bruno, Andrea Passarella

The widespread diffusion of mobile phones is triggering an exponential growth of mobile data traffic that is likely to cause, in the near future, considerable traffic overload issues even in last-generation cellular netw…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)