The Funded Grant

In academic years 2020–21 and 2021–22, ÑÇÉ«Ó°¿â received funds in a very competitive program, NCAE-C Cyber Curriculum and Research 2020 Program, that is supported by the National Security Agency to conduct state-of-the-art research study focusing on improving IoT systems' security.

Project Description

The title of the funded project is "Investigating Effective and Efficient Anomaly Detection on IoT Systems via a Novel Fusion of Deep Learning Techniques." Its main goal is to develop a practical framework (that is based on a sound theoretical foundation) for the IoT anomaly detection in order to assess and improve the impact IoT systems have on the security of various networks.

To achieve the project objectives, the project will develop a prototype for simulation and evaluation of the detection algorithms. This includes simulation and initial evaluation of the detection algorithms, as well as, corresponding data results regarding the performance and efficiency of the algorithms. Then, it will develop a physical testbed for further analysis and evaluation of the anomaly detection scheme. This includes an outline of architecture and implementation of IoT system, see the figure below for a proposed prototype for a smart building model.

IoT Device DiagramProject Outcomes

So far, work on this project has resulted in the following publications/presentations:

  • Z. Good, W. Farag, X-W. Wu, S. Ezekiel, M. Balega, F. May, and A. Deak, “Comparative Analysis of Machine Learning Techniques for IoT Anomaly Detection Using the NSL-KDD Dataset,” to appear in the , ISSN: 1738-7906, Vol.23, No.1, Jan. 2023
  • M. Balega, W. Farag, S. Ezekiel, X. Wu, A. Deak, and Z. Good, “IoT Anomaly Detection Using a Multitude of Machine Learning Algorithms,” in the proceedings of the Oct. 11-13, 2022, Washington, DC.
  • A. Robbins, W. Farag, X-W Wu, P. Chuadry, and S. Ezekiel, "Zigbee as a Candidate Standard for Use in Anomaly Detection in IoT LANs," in the , held virtually, April 11-14, 2021.
  • F. May, “Anomaly Detection Within IoT Devices Using The NSL-KDD Dataset,” A poster presentation at the ÑÇÉ«Ó°¿â Scholars Forum held on April 2022. This poster won the 3rd place in Sigma Xi Awards for undergraduate Poster. Faculty mentor, Waleed Farag.
  • M. Balega, “IoT Anomaly Detection Using a Multitude of ML Algorithms,”. A poster presentation at the ÑÇÉ«Ó°¿â Scholars Forum held on April 2022. This poster won the Women in STEM Outstanding Poster, Undergraduate. Faculty mentor, Waleed Farag. 
  • Alicia Deak, “Comparative Study of IoT-TON Machine Learning Algorithms,” A poster presentation at the ÑÇÉ«Ó°¿â Scholars Forum held on April 2022. This poster won the S-COAM graduate poster award. Faculty mentor, S. Ezekiel.
  • A. Robbins, C. Lefever, W. Farag, X-W Wu, and S. Ezekiel, "The Building Blocks of a Zigbee-centered IDS for IoT Smart Buildings,", a poster presentation at the ÑÇÉ«Ó°¿â Scholars Forum held on April 8, 2021.

Project Meetings and Documents

Waleed Farag, the project director, the two Co-PIs, Drs. Wu and Ezekiel, and all student researchers are holding regular weekly meetings since early fall 2020. In these meetings, we address outstanding challenges, report of progress, and identify and assign research tasks for the next week. Listed below are detailed meeting documents  for this IoT Anomaly Detection Research Project.

2022–23

2020–21