The development of an internet of things (Iot) network traffic dataset with simulated attack data.

• Main Authors: Stiawan, Deris, Wahyudi, Dimas, Septian, Tri Wanda, Idris, Mohd. Yazid, Budiarto, Rahmat
• Format: Article
• Language: English
• Published: Taiwan Academic Network Management Committee 2023
• Subjects: T58.5-58.64 Information technology
• Online Access: http://eprints.utm.my/106766/1/MohdYazidIdris2023_TheDevelopmentofanInternetofThings%20IoTNetworkTraffic.pdf; http://eprints.utm.my/106766/; http://dx.doi.org/10.53106/160792642023032402013
• Institution: Universiti Teknologi Malaysia

Due to the complexity and multifaceted nature of Internet of Things (IoT) networks/systems, researchers in the field of IoT network security complain about the rareness of real life-based datasets and the limitation of heterogeneous of communication protocols used in the datasets. There are a number of datasets publicly available such as DARPA, Twente, ISCX2012, ADFA, CIC-IDS2017, CSE-CICIDS2018, CIC-DDOS2019, MQTT-IoT-IDS-2020, and UNSW-NB15 that have been used by researchers to evaluate performance of the Intrusion Detection Systems (IDSs), nevertheless, the datasets creation are not based on real-life scenarios and rely only on one communication protocol. This paper produces a dataset that is created using real-life scenarios. The data are captured from an IoT test-bed network consists of six sensors running IEEE 802.11 (WiFi) and IEEE 802.15.4 (ZigBee) communication protocols and considering normal as well as attacks traffics. Furthermore, the robustness of the dataset for recognizing the types of data traffics is evaluated using Intrusion Detection Engine (IDE) with Naïve String Matching. The experiments on dataset robustness show promising results, i.e.: Accuracy level of 99.92%, Precision of 100%, False Positive Rate (FPR) of 0, and False Negative Rate (FPR) of 0.0869.