论文标题
COAP-DOS：IOT网络入侵数据集
CoAP-DoS: An IoT Network Intrusion Dataset
论文作者
论文摘要
随着物联网设备越来越集成到重要网络，对安全互联网（IoT）设备的需求正在增长。许多系统依靠这些设备保持可用并提供可靠的服务。由于这些低功率设备非常容易受到拒绝服务攻击，因此拒绝对IoT设备的服务攻击是一个真正的威胁。启用机器学习的网络入侵检测系统可有效识别新威胁，但是它们需要大量数据才能正常工作。有许多网络流量数据集，但很少有人关注物联网网络流量。在物联网网络数据集中，缺乏coap拒绝服务数据。我们提出了一个涵盖此差距的新型数据集。我们通过从真正的COAP拒绝服务攻击中收集网络流量来开发新的数据集，并在多个不同的机器学习分类器上比较数据。我们证明数据集对许多分类器有效。
The need for secure Internet of Things (IoT) devices is growing as IoT devices are becoming more integrated into vital networks. Many systems rely on these devices to remain available and provide reliable service. Denial of service attacks against IoT devices are a real threat due to the fact these low power devices are very susceptible to denial-of-service attacks. Machine learning enabled network intrusion detection systems are effective at identifying new threats, but they require a large amount of data to work well. There are many network traffic data sets but very few that focus on IoT network traffic. Within the IoT network data sets there is a lack of CoAP denial of service data. We propose a novel data set covering this gap. We develop a new data set by collecting network traffic from real CoAP denial of service attacks and compare the data on multiple different machine learning classifiers. We show that the data set is effective on many classifiers.
