NF-UNSW-NB15-v3

This dataset is an enhanced version of NetFlow-based datasets, incorporating 53 extracted features that provide detailed insights into network flows. The dataset includes binary and multi-class labels, distinguishing between normal traffic and nine different types of attacks. It is structured in CSV format, with each row representing a single network flow, labeled accordingly. One of the key aspects of this dataset is the inclusion of temporal features, which allow for a more detailed analysis of traffic over time. The dataset records precise timestamps for each flow, including start and end times, enabling a more structured understanding of flow duration and activity patterns. Additionally, it captures inter-packet arrival time (IPAT) statistics, including minimum, maximum, average, and standard deviation values for both source-to-destination and destination-to-source packet transmissions.

本数据集为基于NetFlow的增强型数据集，纳入了53项提取特征，可为深入解析网络流量流提供详实支撑。数据集包含二分类与多分类标签，可区分正常流量与九种不同类型的网络攻击。本数据集采用CSV格式存储，每一行对应一条独立的网络流量流并附带对应标签。本数据集的核心特性之一在于纳入了时序特征，能够支持对流量随时间变化的精细化分析。数据集为每条流量流记录了精确的时间戳，包含起始时刻与结束时刻，可助力更结构化地理解流量持续时长与活动模式。此外，数据集还捕获了数据包间到达时间（Inter-Packet Arrival Time, IPAT）的统计信息，涵盖源端到目的端与目的端到源端的数据包传输的最小值、最大值、平均值与标准差。