CoAt-Set: Transformed coordinated attack dataset for collaborative intrusion detection simulationMendeley Data

CoAt-Set: Transformed coordinated attack dataset for collaborative intrusion detection simulationMendeley Data

The CoAt-Set dataset is a transformed dataset specifically designed for collaborative anomaly detection within Collaborative Intrusion Detection Systems (CIDS). It is developed by extracting and relabeling coordinated attack patterns from well-established datasets, including CIC-ToN-IoT, CIC-IDS2017...

Full description

Saved in:
Bibliographic Details
Main Authors: Aulia Arif Wardana, Grzegorz Kołaczek, Parman Sukarno
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:Data in Brief
Subjects:
Cybersecurity
Anomaly detection
Network simulation
Augmented data
Heterogeneous data
Online Access:http://www.sciencedirect.com/science/article/pii/S2352340925000861
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The CoAt-Set dataset is a transformed dataset specifically designed for collaborative anomaly detection within Collaborative Intrusion Detection Systems (CIDS). It is developed by extracting and relabeling coordinated attack patterns from well-established datasets, including CIC-ToN-IoT, CIC-IDS2017, CIC-UNSW-NB15, CSE-CIC-IDS2018, CIC-BoT-IoT, Distrinet-CIC-IDS2017, and NF-UQ-NIDS. CoAt-Set focuses on coordinated attack scenarios such as large-scale stealthy scans, worm outbreaks, and distributed denial-of-service (DDoS) attacks, simulating realistic and high-impact threats that commonly observed in modern networks. The transformation process involved organizing coordinated attack behaviors and providing detailed annotations and network traffic features, enhancing its relevance for anomaly detection in collaborative environments. CoAt-Set is compatible with standard machine learning frameworks, offering researchers and practitioners a comprehensive resource for developing, testing, and evaluating CIDS models. It is suitable for various applications, including collective threat intelligence research, analyzing distributed threat patterns, developing machine learning algorithms for distributed systems, and training simulations designed for heterogeneous network environments.
ISSN:2352-3409

Similar Items