Umair Mughal

Umair Mughal

I am a PhD Candidate at the Computer Science Department at Tennessee Tech University.

Publications

Journals Publications (Updated)

  1. U. A. Mughal, R. Atat, and M. Ismail, “Next-Gen Defense: an Architecture-Independent Sequential Ensemble Learning for Intrusion Detection in a Swarm of UAVs,”, in IEEE Transactions on Intelligent Transportation Systems (2024). (Under Review) (IF: 8.5)

  2. U. A. Mughal, I. Ahmad, and C. Yuen, “Ensemble Learning-Based Intrusion Detection System for RIS-Assisted V2X Communication”, in IEEE Transactions on Consumer Electronics (2024). (Under Review) (IF: 4.3)

  3. I. Ahmad, R. Narmeen, U. A. Mughal, and K. H. Chang, “ Optimizing Cell Association and Stability in Integrated Aerial-to-Ground Next-Generation Consumer Wireless Networks,” in IEEE Transactions on Consumer Electronics (2024). (Under Review) (IF: 4.3)

  4. U. A. Mughal, Y. Alkhrijah, A. Almadhor, C. Yuen, “ Deep Learning for Secure UAV-Assisted RIS Communication Networks”, Internet of Thing Magazine (2024). (PDF)

  5. S. C. Hassler, U. A. Mughal, and M. Ismail, “Cyber-Physical Intrusion Detection System for Unmanned Aerial Vehicles,” in IEEE Transactions on Intelligent Transportation Systems (2023). IF: 8.5 (PDF) (code)

  6. U. A. Mughal, J. Xiao, I. Ahmad, and K. H. Chang, “Cooperative Resource Management for Cellular V2I Communications in a Dense Urban Environment”, in Vehicular Communications 26 (2020). IF: 6.7 (PDF) (code)

  7. R. Narmeen, I. Ahmad, Z. Kaleem, U. A. Mughal, D. B. Da Costa and S. Muhaidat, “Shortest Propagation Delay-Based Relay Selection for Underwater Acoustic Sensor Networks,” in IEEE Access, vol. 9, pp. 37923-37935, 2021, doi: 10.1109/ACCESS.2021.3061273. IF: 3.9 (PDF)

  8. U. A. Mughal, I. Ahmad, C. J. Pawase, and K. H. Chang. “UAVs path planning by particle swarm optimization based on visual-SLAM algorithm,” In Intelligent Unmanned Air Vehicles Communications for Public Safety Networks, pp. 169-197. Singapore: Springer Nature Singapore, 2022. (PDF) (code)

Conference

  1. U. A. Mughal, R. Atat, and M. Ismail, Graph Neural Network-based Intrusion Detection System for a Swarm of UAVs”, in 2024 IEEE Military Communications Conference (MILCOM-2024), Washington, DC, USA. (Under Review)

  2. John Richeson, U. A. Mughal, A. Takiddin, and M. Ismail, “Robust UAV Intrusion Detection System Against Adversarial Evasion Attacks”, in 2024 IEEE Military Communications Conference (MILCOM-2024), Washington, DC, USA. (Under Review)

  3. U. A. Mughal, S. C. Hassler and M. Ismail, “Machine Learning-Based Intrusion Detection for Swarm of Unmanned Aerial Vehicles,” 2023 IEEE Conference on Communications and Network Security (CNS), Orlando, FL, USA, 2023, pp. 1-9, doi: 10.1109/CNS59707.2023.10288962. (PDF) (code)

  4. U. A. Mughal, M. Ismail and S. A. A. Rizvi, “Stealthy False Data Injection Attack on Unmanned Aerial Vehicles with Partial Knowledge,” 2023 IEEE Conference on Communications and Network Security (CNS), Orlando, FL, USA, 2023, pp. 1-9, doi: 10.1109/CNS59707.2023.10289001. (PDF) (code)

  5. N. Ahmad, U. A. Mughal, K. H. Change, “3D Path Planning of Unmanned Aerial Vehicles,” 2020 Korea Communications Society Conference, Korea, 2020, pp. 43 - 435. (PDF)

  6. U. A. Mughal, I. Ahmad, and K. H. Chang, “Cellular V2X communications in unlicensed spectrum: Compatible coexistence with VANET in 5G systems”, in Proc. JCCI 2019: 29th Joint Communication and Information Conference, May 2019 (PDF)

  7. U. A. Mughal, I. Ahmad, K. H. Chang, “Virtual cells operation for 5G V2X communications,” 2019 Korea Communications Society Conference, Korea, 2019, pp. 1486 - 1487. (PDF)

Dataset:

Cyber-Physical Dataset for UAVs Under Normal Operations and Cyber-attacks [Download on IEEE DataPort].

The dataset is the first of its kind and collected from the actual drone system. It contains cyber (communication) and physical (behavioral) features under cyberattacks and normal operations of the drone. There is no dataset available that captures both cyber and physical features.

The fusion of cyber and physical data provides a comprehensive representation of a UAV’s operational state. While cyber data captures anomalies in communication patterns, physical data reveals discrepancies in flight dynamics and sudden changes in behavior such as roll, pitch, yaw angles, acceleration, etc. By fusing these data streams, we construct a detailed depiction of the UAV’s state across cyber and physical domains. This fusion enables accurate detection of attacks that might be missed when only one type of data is considered.

The following cyberattacks has been executed to collect the data.

Software and Simulator

More detail on my Google Scholar