# FENXI: Deep-learning Traffic Analytics at the Edge

arXiv: https://arxiv.org/abs/2105.11738 · HTML: https://mlsanity.com/paper/2105.11738/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 12 of 12)

- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [Experience-driven Networking: A Deep Reinforcement Learning based Approach](https://mlsanity.com/paper/1801.05757/) (2018)
- [Rafiki: Machine Learning as an Analytics Service System](https://mlsanity.com/paper/1804.06087/) (2018)
- [PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems](https://mlsanity.com/paper/1810.06115/) (2018)
- [pForest: In-Network Inference with Random Forests](https://mlsanity.com/paper/1909.05680/) (2019)
- [Knowledge-Defined Networking](https://mlsanity.com/paper/1606.06222/) (2016)
- [DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification](https://mlsanity.com/paper/1711.08336/) (2017)
- [Running Neural Networks on the NIC](https://mlsanity.com/paper/2009.02353/) (2020)
- [In-network Neural Networks](https://mlsanity.com/paper/1801.05731/) (2018)
- [MoonGen: A Scriptable High-Speed Packet Generator](https://mlsanity.com/paper/1410.3322/) (2014)
- [Net2Vec: Deep Learning for the Network](https://mlsanity.com/paper/1705.03881/) (2017)

## Built on by (most cited first, 5 of 5)

- [Autonomous GIS: the next-generation AI-powered GIS](https://mlsanity.com/paper/2305.06453/) (2023)
- [Hardware-Aware Neural Architecture Search for Encrypted Traffic Classification on Resource-Constrained Devices](https://mlsanity.com/paper/2506.11319/) (2025)
- [Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks](https://mlsanity.com/paper/2205.08347/) (2022)
- [Inference-to-complete: A High-performance and Programmable Data-plane Co-processor for Neural-network-driven Traffic Analysis](https://mlsanity.com/paper/2411.00408/) (2024)
- [RepTC: Representation-Aware Optimization for Efficient Traffic Classification on Edge IoT Devices](https://mlsanity.com/paper/2610.04784/) (2026)

## Abstract (arXiv)

Live traffic analysis at the first aggregation point in the ISP network enables the implementation of complex traffic engineering policies but is limited by the scarce processing capabilities, especially for Deep Learning (DL) based analytics. The introduction of specialized hardware accelerators i.e., Tensor Processing Unit (TPU), offers the opportunity to enhance the processing capabilities of network devices at the edge. Yet, to date, no packet processing pipeline is capable of offering DL-based analysis capabilities in the data-plane, without interfering with network operations. In this paper, we present FENXI, a system to run complex analytics by leveraging TPU. The design of FENXI decouples forwarding operations and traffic analytics which operates at different granularities i.e., packet and flow levels. We conceive two independent modules that asynchronously communicate to exchange network data and analytics results, and design data structures to extract flow level statistics without impacting per-packet processing. We prototyped and evaluated FENXI on general-purpose servers considering both adversarial and realistic network conditions. Our analysis shows that FENXI can sustain 100 Gbps line rate traffic processing requiring only limited resources, while also dynamically adapting to variable network conditions.