UNSW-NB15 (UNSQ-NB15)

“UNSW-NB 15 数据集的原始网络数据包由新南威尔士大学堪培拉网络靶场实验室的 IXIA PerfectStorm 工具创建，用于生成真实现代正常活动和合成当代攻击行为的混合体。使用了 tcpdump 工具捕获 100 GB 的原始流量（例如，Pcap 文件）。该数据集有九种攻击类型，即 Fuzzers、Analysis、Backdoors、DoS、Exploits、Generic、Reconnaissance、Shellcode 和 Worms。Argus、Bro-IDS 工具使用了 12 种算法，总共生成了 49 个带有类标签的特征。这些特征在 UNSW-NB15_features.csv 文件中进行了描述。总共有 200 万条记录和 540,044 条记录存储在四个 CSV 文件中，即， UNSW-NB15_1.csv、UNSW-NB15_2.csv、UNSW-NB15_3.csv 和 UNSW-NB15_4.csv。地面实况表名为 UNSW-NB15_GT.csv，事件文件列表名为 UNSW-NB15_LIST_EVENTS.csv。来自该数据集的分区被配置为训练集nd 测试集，分别为 UNSW_NB15_training-set.csv 和 UNSW_NB15_testing-set.csv。训练集中的记录数为 175,341 条记录，测试集为 82,332 条记录，来自不同类型，攻击和正常。"

The raw network packets of the UNSW-NB15 dataset were created by the IXIA PerfectStorm tool in the Cyber Range Lab of the University of New South Wales Canberra to generate a hybrid of real modern normal network activities and synthetic contemporary attack behaviors. The tcpdump tool was employed to capture 100 GB of raw traffic (e.g., Pcap files). This dataset encompasses nine types of attacks, namely Fuzzers, Analysis, Backdoors, DoS, Exploits, Generic, Reconnaissance, Shellcode and Worms. Twelve algorithms were utilized via the Argus and Bro-IDS tools to generate a total of 49 features with class labels, which are detailed in the UNSW-NB15_features.csv file. A total of 2,000,000 records and 540,044 records are stored in four CSV files: UNSW-NB15_1.csv, UNSW-NB15_2.csv, UNSW-NB15_3.csv and UNSW-NB15_4.csv. The ground truth table is named UNSW-NB15_GT.csv, and the event file list is named UNSW-NB15_LIST_EVENTS.csv. The partitions derived from this dataset are configured as the training set and test set, namely UNSW_NB15_training-set.csv and UNSW_NB15_testing-set.csv respectively. The training set contains 175,341 records, while the test set contains 82,332 records, covering diverse types of both attack and normal network traffic.

搜集汇总

背景与挑战

背景概述

UNSW-NB15是一个网络安全数据集，包含九种攻击类型的混合数据，总记录数为200万条，分为训练集和测试集。数据集由新南威尔士大学创建，用于入侵检测研究。