Dalhousie NIMS Lab VPN 2024 Dataset

Citation Author(s):
Haotian
Liu
Riyad
Alshammari
Nur
Zincir-Heywood
Submitted by:
Haotian Liu
Last updated:
Mon, 12/02/2024 - 13:09
DOI:
10.21227/08yh-pz10
Data Format:
*.avi; *.csv; *.txt
Research Article Link:
Edge-Cloud VPN Traffic Analysis Over Cross Platforms
License:
Creative Commons Attribution
292 Views
Categories:
Wireless Networking
IoT
Machine Learning
Security
Standards Research Data
Keywords:
VPN, encrypted network traffic, Machine Learning
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

This dataset presents real-world VPN encrypted traffic flows captured from five applications that belong to four service categories, which reflect typical usage patterns encountered by everyday users. 

Our methodology utilized a set of automatic scripts to simulate real-world user interactions for these applications, to achieve a low level of noise and irrelevant network traffic.

 

The dataset consists of flow data collected from four service categories:

Instant Messaging (Slack for both desktop and Android)

Streaming (Twitch for desktop, and TikTok for Android)

Browsing (Chrome for both desktop and Android)

Cloud Storage Service (Google Drive for both desktop and Android)

 

These flows were extracted from .pcap captures with Tranalyzer. The dataset is organized into service-specific folders, with each containing the “with VPN” and “without VPN” scenario.

Comprehensive details regarding our setup and methodology are provided in our paper, along with a thorough explanation of the dataset's structure in the readme file. 

This dataset serves as a valuable resource for understanding the pattern of VPN encrypted traffic in real-world contexts.

 

Instructions: 

Data Format: The data files are in .txt format, separated by Tabs. They can be converted to .csv files safely. The first row in a flow file contains the names of the flow-level characteristics, and the first column lists the flows.

Further details about the method we used to generate, capture and label the VPN data can be found in our paper below:

[1] Haotian Liu, Riyad Alshammari, Nur Zincir-Heywood, "Edge-Cloud VPN Traffic Analysis Over Cross Platforms”, IEEE World Forum on Internet of Things, 2024.

Link to the paper and DOI: Will be here when posted on IEEE Xplore.

Please refer to the README file for further information.

Dataset Files

LOGIN TO ACCESS DATASET FILES

Documentation

AttachmentSize
File readme.txt4.56 KB

 

QUESTIONS?