大规模城市物联网活动数据集用于DDoS攻击模拟

本数据集由南加州大学创建，包含4060个节点在一个月内的时空活动数据，用于模拟和检测分布式拒绝服务（DDoS）攻击。数据集记录了每个节点的二进制活动状态，时间粒度为30秒。为增强数据集的实用性，还提供了一个合成DDoS攻击生成器，可根据可调参数如攻击节点数和持续时间注入攻击活动。该数据集旨在通过机器学习算法，特别是深度神经网络，来训练和评估DDoS攻击的检测和防御机制。

This dataset, developed by the University of Southern California, encompasses spatio-temporal activity data of 4060 nodes collected over a one-month period for the purpose of simulating and detecting distributed denial-of-service (DDoS) attacks. It records the binary activity state of each node, with a time granularity of 30 seconds. To improve its practical applicability, a synthetic DDoS attack generator is also included, which enables the injection of attack traffic according to adjustable parameters such as the number of attacking nodes and attack duration. This dataset is intended for training and evaluating DDoS attack detection and defense mechanisms via machine learning algorithms, particularly deep neural networks.