Saif Syaifuddin, Widyawan Widyawan, Ferdiana Ridi
Department of Electrical and Information Technology, Universitas Gadjah Mada, Jl. Grafika 2, Yogyakarta 55281, Indonesia.
Department of Information Technology, Universitas Muhammadiyah Malang, Jl. Raya Tlogomas 246, Malang 65144, Indonesia.
Data Brief. 2024 May 6;54:110496. doi: 10.1016/j.dib.2024.110496. eCollection 2024 Jun.
The proliferation of Internet of Things devices has ushered in a new era of connectivity and con-venience, yet it has also exposed a myriad of security challenges, with Distributed Denial of Service attacks posing a significant threat. This paper introduces the IoT-DH dataset, a novel and extensive dataset designed for the purpose of classifying, identifying, and detecting DDoS attacks within IoT ecosystems. The dataset encompasses diverse scenarios and network configurations, providing a realistic representation of IoT environments. We present a systematic analysis of the IoT-DH dataset, exploring its features and characteristics that mirror the complexities of real-world IoT net-works. The dataset includes a variety of attack scenarios, incorporating different attack vectors and intensities to capture the evolving nature of DDoS threats in IoT. Our approach facilitates the development and evaluation of robust machine learning and deep learning models for effective DDoS attack mitigation. Furthermore, we propose a multi-faceted methodology for leveraging the IoT-DH dataset, encompassing classification techniques to categorize attack types, identification mechanisms to pinpoint malicious entities, and detection algorithms to promptly respond to ongoing DDoS incidents. The efficacy of these methodologies is demonstrated through extensive experiments and evaluations, showcasing their ability to enhance the security posture of IoT environments.
物联网设备的激增开启了一个连接性和便利性的新时代，但同时也暴露出了无数安全挑战，分布式拒绝服务攻击构成了重大威胁。本文介绍了IoT-DH数据集，这是一个新颖且广泛的数据集，旨在对物联网生态系统中的分布式拒绝服务攻击进行分类、识别和检测。该数据集涵盖了各种场景和网络配置，真实地呈现了物联网环境。我们对IoT-DH数据集进行了系统分析，探究了其反映现实世界物联网网络复杂性的特征。该数据集包括各种攻击场景，融入了不同的攻击向量和强度，以捕捉物联网中分布式拒绝服务威胁的演变特性。我们的方法有助于开发和评估用于有效缓解分布式拒绝服务攻击的强大机器学习和深度学习模型。此外，我们提出了一种利用IoT-DH数据集的多方面方法，包括用于对攻击类型进行分类的分类技术、用于确定恶意实体的识别机制以及用于对正在进行的分布式拒绝服务事件迅速做出响应的检测算法。通过广泛的实验和评估证明了这些方法的有效性，展示了它们增强物联网环境安全态势的能力。
