Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NetBench: A Large-Scale and Comprehensive Network Traffic Benchmark Dataset for Foundation Models

Chen Qian, Xiaochang Li, Qineng Wang, Gang Zhou, Huajie Shao

TL;DR

The NetBench is introduced, a large-scale and comprehensive bench-mark dataset for assessing machine learning models, especially foundation models, in both network traffic classification and generation tasks and shows that foundation models significantly outperform the traditional deep learning methods in traffic classification.

Abstract

In computer networking, network traffic refers to the amount of data transmitted in the form of packets between internetworked computers or Cyber-Physical Systems. Monitoring and analyzing network traffic is crucial for ensuring the performance, security, and reliability of a network. However, a significant challenge in network traffic analysis is to process diverse data packets including both ciphertext and plaintext. While many methods have been adopted to analyze network traffic, they often rely on different datasets for performance evaluation. This inconsistency results in substantial manual data processing efforts and unfair comparisons. Moreover, some data processing methods may cause data leakage due to improper separation of training and testing data. To address these issues, we introduce the NetBench, a large-scale and comprehensive benchmark dataset for assessing machine learning models, especially foundation models, in both network traffic classification and generation tasks. NetBench is built upon seven publicly available datasets and encompasses a broad spectrum of 20 tasks, including 15 classification tasks and 5 generation tasks. Furthermore, we evaluate eight State-Of-The-Art (SOTA) classification models (including two foundation models) and two generative models using our benchmark. The results show that foundation models significantly outperform the traditional deep learning methods in traffic classification. We believe NetBench will facilitate fair comparisons among various approaches and advance the development of foundation models for network traffic. Our benchmark is available at https://github.com/WM-JayLab/NetBench.

NetBench: A Large-Scale and Comprehensive Network Traffic Benchmark Dataset for Foundation Models

TL;DR

The NetBench is introduced, a large-scale and comprehensive bench-mark dataset for assessing machine learning models, especially foundation models, in both network traffic classification and generation tasks and shows that foundation models significantly outperform the traditional deep learning methods in traffic classification.

Abstract

In computer networking, network traffic refers to the amount of data transmitted in the form of packets between internetworked computers or Cyber-Physical Systems. Monitoring and analyzing network traffic is crucial for ensuring the performance, security, and reliability of a network. However, a significant challenge in network traffic analysis is to process diverse data packets including both ciphertext and plaintext. While many methods have been adopted to analyze network traffic, they often rely on different datasets for performance evaluation. This inconsistency results in substantial manual data processing efforts and unfair comparisons. Moreover, some data processing methods may cause data leakage due to improper separation of training and testing data. To address these issues, we introduce the NetBench, a large-scale and comprehensive benchmark dataset for assessing machine learning models, especially foundation models, in both network traffic classification and generation tasks. NetBench is built upon seven publicly available datasets and encompasses a broad spectrum of 20 tasks, including 15 classification tasks and 5 generation tasks. Furthermore, we evaluate eight State-Of-The-Art (SOTA) classification models (including two foundation models) and two generative models using our benchmark. The results show that foundation models significantly outperform the traditional deep learning methods in traffic classification. We believe NetBench will facilitate fair comparisons among various approaches and advance the development of foundation models for network traffic. Our benchmark is available at https://github.com/WM-JayLab/NetBench.
Paper Structure (9 sections, 2 figures, 5 tables)

This paper contains 9 sections, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. NetBench
  4. Data Preparation
  5. Tasks in NetBench
  6. Experiments
  7. Experimental Settings
  8. Evaluation Results
  9. Conclusion

Figures (2)

  • Figure 1: The format of network traffic data, which are the mixture of plaintext header and encrypted payload. This mixture makes it hard to directly process with text tokenizers for model training.
  • Figure 2: The overall pipeline of data preparation, consisting of three parts: Data Pre-Processing, Data Standardization, and Data Segmentation. Firstly, we convert flows extracted from network traffic PCAP files into a hexadecimal format. Then, the WordPiece algorithm is employed to segment the hexadecimal data into 4-digit blocks, incorporating specific symbols (</s> for sequence ends, <head> for header separation, and <pkt> for packet demarcation). Lastly, we create two different types of dataset based on flow level and packet level.