IoT-DH dataset for classification, identification, and detection DDoS attack in IoT.
Syaifuddin Saif1,2, Widyawan Widyawan1, Ridi Ferdiana1
1Department of Electrical and Information Technology, Universitas Gadjah Mada, Jl. Grafika 2, Yogyakarta 55281, Indonesia.
Related Experiment Videos
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
07:49Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
Published on: November 26, 2019
07:13Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
Published on: February 25, 2021
View abstract on PubMed
This study introduces the IoT-DH dataset for detecting Distributed Denial of Service (DDoS) attacks in Internet of Things (IoT) ecosystems. It enables the development of machine learning models to classify, identify, and mitigate these significant cyber threats.
Area of Science:
- Computer Science
- Cybersecurity
- Network Security
Background:
- The rapid expansion of Internet of Things (IoT) devices introduces significant security vulnerabilities.
- Distributed Denial of Service (DDoS) attacks represent a major threat to the integrity and availability of IoT ecosystems.
- Existing datasets may not fully capture the complexity and diversity of modern IoT network environments and attack vectors.
Purpose of the Study:
- To introduce the IoT-DH dataset, a comprehensive resource for DDoS attack analysis in IoT.
- To facilitate the development and evaluation of machine learning and deep learning models for DDoS attack mitigation in IoT.
- To provide a realistic benchmark for classifying, identifying, and detecting DDoS attacks within diverse IoT scenarios.
Main Methods:
- Development and systematic analysis of the novel IoT-DH dataset, encompassing various network configurations and attack scenarios.
- Exploration of dataset features that reflect real-world IoT complexities and evolving DDoS threats.
- Proposal of a multi-faceted methodology for DDoS attack mitigation, including classification, identification, and detection algorithms.
Main Results:
- The IoT-DH dataset provides a realistic representation of IoT environments with diverse attack vectors and intensities.
- The proposed methodologies demonstrate efficacy in classifying, identifying, and detecting DDoS attacks within the dataset.
- Experimental evaluations confirm the ability of the developed approaches to enhance IoT security posture.
Conclusions:
- The IoT-DH dataset is a valuable resource for advancing research in IoT cybersecurity, specifically for DDoS attack mitigation.
- The proposed methodologies offer a robust framework for developing effective defense mechanisms against DDoS threats in IoT.
- The findings highlight the importance of comprehensive datasets and advanced algorithms for securing interconnected IoT environments.