CIC IoT dataset 2023

A real-time dataset and benchmark for large-scale attacks in IoT environment

The main goal of this research is to propose a novel and extensive IoT attack dataset to foster the development of security analytics applications in real IoT operations. To accomplish this, 33 attacks are executed in an IoT topology composed of 105 devices.

These attacks are classified into seven categories, namely DDoS, DoS, Recon, Web-based, Brute Force, Spoofing, and Mirai. Finally, all attacks are executed by malicious IoT devices targeting other IoT devices.

The main contributions of this research are:

• a new realistic IoT attack dataset, using an extensive topology compose of several real IoT devices and adopting IoT devices as attackers and victims;

• We perform, document, and collect data from 33 attacks divided into 7 classes against IoT devices and demonstrated how they can be reproduced;

• We evaluate the performance of machine and deep learning algorithms using the CICIoT2023 dataset to classify and detect IoT network traffic as malicious or benign.

CIC IoT lab

The production of IoT security data that can be used to support real applications is challenging for several reasons. One of the main problems is having an extensive network composed of several real IoT devices, similar to topologies of real IoT applications.

Many works adopt simulated or very few IoT devices due to costs, network equipment required (e.g., switches, routers, and network tap), and personnel dedicated to maintaining such an infrastructure.

Thereupon, the Canadian Institute for Cybersecurity (CIC) has a distinguished presence in the cybersecurity ecosystem and a history of high-impact contributions to industry and academia. Examples are datasets used to develop new cybersecurity applications and several partnerships with industry to improve the cybersecurity practice and develop new solutions.

This success enabled CIC to establish an IoT lab with a dedicated network to enable the development of IoT security solutions. In fact, by sharing the data collected from this extensive topology, we intend to foster the advancement of IoT security research and support several initiatives in different IoT security aspects.

Topology chart    Topology diagram

Data descriptions

Feature	mean	std	min	25%	50%	75%	max
flow_duration	5.76544939	285.034171	0	0	0	0.10513809	394357.207
Header_Length	76705.9637	461331.747	0	54	54	280.555	9907147.75
Protocol type	9.06568989	8.94553292	0	6	6	14.33	47
Duration	66.3507169	14.0191881	0	64	64	64	255
Rate	9064.05724	99562.4906	0	2.09185589	15.7542308	117.384754	8388608
Srate	9064.05724	99562.4906	0	2.09185589	15.7542308	117.384754	8388608
Drate	5.46E-06	0.00725077	0	0	0	0	29.7152249
fin_flag_number	0.08657207	0.28120696	0	0	0	0	1
syn_flag_number	0.20733528	0.40539779	0	0	0	0	1
rst_flag_number	0.09050473	0.28690351	0	0	0	0	1
psh_flag_number	0.08775006	0.28293106	0	0	0	0	1
ack_flag_number	0.12343168	0.32893207	0	0	0	0	1
ece_flag_number	1.48E-06	0.00121571	0	0	0	0	1
cwr_flag_number	7.28E-07	0.00085338	0	0	0	0	1
ack_count	0.09054283	0.28643144	0	0	0	0	7.7
syn_count	0.33035785	0.6635354	0	0	0	0.06	12.87
fin_count	0.09907672	0.32711642	0	0	0	0	248.32
urg_count	6.23982356	71.8524536	0	0	0	0	4401.7
rst_count	38.4681213	325.384658	0	0	0	0.01	9613
HTTP	0.04823423	0.21426079	0	0	0	0	1
HTTPS	0.05509922	0.22817383	0	0	0	0	1
DNS	0.00013068	0.01143079	0	0	0	0	1
Telnet	2.14E-08	0.00014635	0	0	0	0	1
SMTP	6.43E-08	0.00025349	0	0	0	0	1
SSH	4.09E-05	0.00639772	0	0	0	0	1
IRC	1.50E-07	0.00038722	0	0	0	0	1
TCP	0.57383427	0.49451846	0	0	1	1	1
UDP	0.21191758	0.40866676	0	0	0	0	1
DHCP	1.71E-06	0.00130903	0	0	0	0	1
ARP	6.62E-05	0.00813521	0	0	0	0	1
ICMP	0.16372157	0.37002273	0	0	0	0	1
IPv	0.99988731	0.01061485	0	1	1	1	1
LLC	0.99988731	0.01061485	0	1	1	1	1
Tot sum	1308.32257	2613.30273	42	525	567	567.54	127335.8
Min	91.6073456	139.695326	42	50	54	54	13583
Max	181.963418	524.030902	42	50	54	55.26	49014
AVG	124.668815	240.991485	42	50	54	54.0497296	13583
Std	33.3248065	160.335722	0	0	0	0.37190955	12385.2391
Tot size	124.691567	241.549341	42	50	54	54.06	13583
IAT	83182525.9	17047351.7	0	83071566	83124522.4	83343908	167639436
Number	9.49848933	0.81915318	1	9.5	9.5	9.5	15
Magnitue	13.12182	8.62857895	9.16515139	10	10.3923048	10.3967148	164.821115
Radius	47.0949848	226.769647	0	0	0	0.50592128	17551.2708
Covariance	30724.3565	323710.68	0	0	0	1.34421569	154902159
Variance	0.0964376	0.233001	0	0	0	0.08	1
Weight	141.51237	21.0683073	1	141.55	141.55	141.55	244.6

Dataset directories

The main dataset directory (CICIoT2023) contains four subdirectories related to different files, namely:

1. PCAP: Contains the original traffic captured during the attacks as .pcp files;

2. CSV: Contains features extracted from the original files to be used in the Machine Learning (ML) evaluation (.csv files);

3. Example: A jupyter notebook that shows how the dataset can be used to train and evaluate Machine Learning (ML) models in attack detection and classification;

4. Supplementary material: Source code and description of tools used throughout the process of collecting and wrangling the attack data. We used Mergecap to merge multiple .pcap files, PySpark to handle the data, TCPDump to split the .pcap files in multiple smaller files, and DPKT to extract features.

Acknowledgments

The authors would like to thank the Canadian Institute for Cybersecurity (CIC) for its financial and educational support.

Using the dataset

Webinar explanation about CIC IoT datasets: "From Profiling to Protection: Leveraging Datasets for Enhanced IoT Security" by Dr. Sajjad Dadkhah, Assistant Professor and Cybersecurity R&D Team Lead with Q&A by Sumit Kundu.

YouTube video: IoTProMo: Securing IoT Networks using Device Profiling and Monitoring by Alireza Zohourian with Q&A by Sumit Kundu.

Citation

E. C. P. Neto, S. Dadkhah, R. Ferreira, A. Zohourian, R. Lu, A. A. Ghorbani. "CICIoT2023: A real-time dataset and benchmark for large-scale attacks in IoT environment," Sensor (2023) – (submitted to Journal of Sensors).

Download the dataset