车载网关-域控以太网入侵检测数据集

本研究引入了车载网关-域控以太网入侵检测数据集。该数据集包含五个子数据集，分别模拟了良性流量和四种典型的恶意流量（延迟攻击、丢包攻击、序列错乱攻击以及传输时间戳抖动攻击）。这些数据集通过精心设计的实验环境生成，能够真实反映车载网络中的正常和异常流量特征。数据集采用滑动窗口方法提取时间序列特征，并结合LSTM递归神经网络进行建模，以提高对网络流量数据的分类准确性和鲁棒性。此外，数据集支持在Windows 10 64位或Linux Ubuntu 18.04/20.04 LTS环境下运行，并建议使用NVIDIA GPU加速训练过程，大小为428MB。

This study introduces a vehicular gateway-domain controller Ethernet intrusion detection dataset. This dataset includes five sub-datasets, which simulate benign traffic and four typical types of malicious traffic respectively: latency attack, packet loss attack, sequence disorder attack, and transmission timestamp jitter attack. These datasets are generated via a meticulously designed experimental environment, which can authentically reflect the normal and abnormal traffic characteristics in vehicular networks. The dataset adopts the sliding window method to extract time-series features, and combines with LSTM recurrent neural network for modeling, so as to enhance the classification accuracy and robustness of network traffic data. In addition, the dataset supports running on Windows 10 64-bit or Linux Ubuntu 18.04/20.04 LTS environments, and it is recommended to use NVIDIA GPUs to accelerate the training process. The total size of the dataset is 428 MB.

搜集汇总

背景与挑战

背景概述

该数据集是一个用于车载网关-域控以太网入侵检测的数据集，包含良性流量和四种典型恶意流量的模拟数据，适用于机器学习模型训练和网络流量分类研究。数据集大小为442.45MB，支持多种操作系统环境，并建议使用GPU加速训练。