CLOUD ATTACK DATASET

With the modern day technological advancements and the evolution of Industry 4.0, it is very important to make sure that the problem of Intrusion detection in Cloud , IoT and other modern networking environments is addressed as an immediate concern. It is a fact that Cloud and Cyber Physical Systems are the basis for Industry 4.0. Thus, intrusion detection in cyber physical systems plays a crucial role in Industry 4.0. Here, we provide the an intrusion detection dataset for performance evaluation of machine learning and deep learning based intrusion detection systems. For this, we have considered, the CIC-IDS 2017 dataset available publicly from Canadian Institute of Cybersecurity. A total of 100541 traffic instances are considered which belong to one of the 14 traffic classes namely bening and thirteen attack classes. All these network instances are converted into traffic images each of 9x9 pixel size. Researchers working on machine learning and deep learning areas can utilize this dataset for their experimental analysis.

随着当代技术进步与工业4.0（Industry 4.0）的演进，针对云计算、物联网（IoT）及其他现代网络环境中的入侵检测问题予以优先处置，已成为至关重要的核心议题。云计算与信息物理系统（Cyber Physical Systems）是工业4.0的底层支撑，因此信息物理系统中的入侵检测在工业4.0中扮演着关键角色。本研究提供一款入侵检测数据集，用于评估基于机器学习（Machine Learning）与深度学习（Deep Learning）的入侵检测系统的性能。本次研究采用加拿大网络安全研究所（Canadian Institute of Cybersecurity）公开发布的CIC-IDS 2017数据集作为基础素材，共选取100541条流量样本，涵盖14个流量类别：1个良性（benign）流量类别与13个攻击流量类别。所有网络流量样本均被转换为尺寸为9×9像素的流量图像。从事机器学习与深度学习领域研究的科研人员可利用本数据集开展相关实验分析工作。