Datasets
Intrusion Detection Datasets:
NSL-KDD Dataset
NSL-KDD is a new version data set of the KDD'99 data set. This is an effective benchmark data set to help researchers compare different intrusion detection methods.
.The setting is composed by 1 training set and 2 testing set:
- KDDTrain+: The full NSL-KDD train set including attack-type labels in CSV format
- KDDTest+: The full NSL-KDD test set including attack-type labels in CSV format
- KDDTest-21: A subset of the KDDTest+ which does not include records with difficulty level of 21 out of 21
UNSW-NB15
UNSW-NB 15 dataset was created by the IXIA PerfectStorm tool in the Cyber Range Lab of the Australian Centre for Cyber Security (ACCS) for generating a hybrid of real modern normal activities and synthetic contemporary attack behaviours.
CICIDS 2017
UCICIDS2017 dataset contains benign and the most up-to-date common attacks, which resembles the true real-world data (PCAPs). It also includes the results of the network traffic analysis using CICFlowMeter with labeled flows based on the time stamp, source and destination IPs, source and destination ports, protocols and attack (CSV files).
The setting is composed by 10 folder each of them contains 10 files. Each file contains 100K data points randomly chosen from the entire dataset. Out of the ten files, one file was used for training and the other nine files were used for testing to measure the classification performance.