Analysis of IoT-23 datasets and machine learning models for malicious traffic detection

• Author(s) / Creator(s)

  • Oha, Chibueze Victor
  • Farouk, Fathima Shakoora
  • Patel, Pujan Pankaj
  • Meka, Prithvi
  • Nekkanti, Sowmya
  • Nayini, Bhageerath
  • Carvalho, Smit Xavier
  • Desai, Nisarg
  • Patel, Manishkumar

• Connected devices are penetrating the market with an unprecedented speed. Networks that carry Internet of Things (IoT) traffic need highly adaptable tools for traffic analysis in order to detect and suppress malicious agents. This has prompted researchers to explore the various benefits machine learning has to offer. By developing models to detect certain kinds of malicious traffic accurately, it will allow for better detection capabilities if implemented in an Intrusion Detection System (IDS) or Next-generation Firewall. This research paper focuses on harnessing the advanced features of Machine Learning (ML) in exploring the network traffic generated by IoT devices. The IoT-23 dataset was used and preprocessed into three different datasets for further exploration using machine learning algorithms. This enhances the easy detection of malicious traffic, thereby improving the security in IoT devices. The machine learning algorithms implemented in this paper include: Logistic Regression, Decision Tree, Random Forest Classifier, XGBoost and Artificial Neural Network. This research was able to achieve almost 100% accuracy across all the three datasets.

• Date created

  2021-04-01

• Subjects / Keywords

  • machine learning
  • IoT-23
  • Internet of Things
  • supervised learning
  • TensorFlow

• Type of Item

  Research Material

• DOI

  https://doi.org/10.7939/r3-2swv-dv28

• License

  Attribution-NonCommercial 4.0 International