Dark Mode
Binary DNS Query Security Dataset
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This resource is dedicated to DNS Tunneling Queries Classification, providing a crucial set of labeled domain names. The purpose is to distinguish between benign network activity and potential threats. Domain names are explicitly categorised into regular queries, assigned the label "0," and those involved in DNS tunnels, assigned the label "1." This data is significant for building and validating machine learning models that focus on identifying malicious network behaviours.
Columns
The dataset is structured with two columns:
- Domain Name/Query: This field holds the text string representing the domain name or DNS query. It contains 14,971 unique values.
- label: The binary target variable for classification. A value of '0' signifies a regular domain name, while '1' indicates a domain name associated with a tunnel.
Distribution
The data is delivered in a CSV file titled
training.csv, approximately 1.94 MB in size. It comprises 15.0k valid entries (100%), with no missing or mismatched values recorded. The distribution of the target variable is highly concentrated, with 3,000 entries corresponding to the '0' label (regular traffic) and 11,999 entries corresponding to the '1' label (tunnels). The mean value for the label column is 0.8, with a standard deviation of 0.4. The update frequency for this material is unspecified.Usage
This data product is ideally suited for training and evaluating binary classification algorithms. The primary use case is developing tools capable of classifying domain names to detect and mitigate network security risks associated with DNS tunneling.
Coverage
The material pertains to general domain names and DNS queries, classified under the tags Websites and DNS. No specific geographic, time range, or demographic scope is detailed in the available information.
License
Attribution 4.0 International (CC BY 4.0).
Who Can Use It
- Data Scientists: For developing robust classification algorithms to identify network anomalies.
- Machine Learning Engineers: For training models that flag suspicious DNS queries.
- Network Security Analysts: For gaining insight into the structure and characteristics of DNS tunneling queries.
Dataset Name Suggestions
- DNS Tunneling Queries Data for Classification
- Binary DNS Query Security Dataset
- Network Tunnel Detection Query Log
Attributes
Original Data Source:Binary DNS Query Security Dataset
QUALITYLoading...