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.


Dataset with diverse type of attacks in Programmable Logic Controllers:

1- Denial of Service 

  • Flooding
  • Amplification/Volumetric

2- Man in the Middle


The full documentation of the dataset is available at: https://arxiv.org/abs/2103.09380 


Boğaziçi University DDoS dataset (BOUN DDoS) is generated in Boğaziçi University via Hping3 traffic generator software by flooding TCP SYN, and UDP packets. This dataset includes attack-free user traffic as well as attack traffic and suitable for evaluating network-based DDoS detection methods. Attacks are towards one victim server connected to the backbone router of the campus.  Attack packets have randomly generated spoofed source  IP addresses.  The data-trace was recorded on the backbone and included over 4000 active hosts.

This work intend to identify characteristics in network traffic that are able to distinguish the normal network behavior from denial of service attacks. One way to classify anomalous traffic is the data analysis of the packets header. This dataset contains labeled examples of normal traffic (23.088 instances), TCP Flood attacks (14.988 instances), UDP Flood (6.894 instances), HTTP Flood (347 instances) and HTTP Slow (183 instances) distributed in 73 numeric variables.