Publications, Patent & Talks

Publications:

  • Faisal, M.A., Aung, Z., Williams, J.R. and Sanchez, A., 2012, May. Securing advanced metering infrastructure using intrusion detection system with data stream mining. In Pacific-Asia Workshop on Intelligence and Security Informatics (pp. 96-111). (Won best paper award)
  • Perera, K.S., Neupane, B., Faisal, M.A., Aung, Z. and Woon, W.L., 2013. A novel ensemble learning-based approach for click fraud detection in mobile advertising. In Mining Intelligence and Knowledge Exploration (pp. 370-382).
  • Faisal, M.A., Aung, Z., Woon, W.L. and Svetinovic, D., 2014, November. Augmented Query Strategies for Active Learning in Stream Data Mining. In International Conference on Neural Information Processing (pp. 431-438).
  • Oentaryo, R.J., Lim, E.P., Finegold, M., Lo, D., Zhu, F., Phua, C., Cheu, E.Y., Yap, G.E., Sim, K., Nguyen, M.N. and Perera, K.S., 2014. Detecting click fraud in online advertising: a data mining approach. In Journal of Machine Learning Research, 15(1), pp.99-140.
  • Faisal, M.A., Aung, Z., Williams, J.R. and Sanchez, A., 2015. Data-stream-based intrusion detection system for advanced metering infrastructure in smart grid: A feasibility study. In IEEE Systems Journal, 9(1), pp.31-44.
  • Faisal, M., Cardenas, A.A. and Mashima, D., 2015, November. How the quantity and quality of training data impacts re-identification of smart meter users?. In 2015 IEEE International Conference on Smart Grid Communications (SmartGridComm) (pp. 31-36).
  • David I. Urbina, Jairo Giraldo, Alvaro A. Cárdenas, Nils Ole Tippenhauer, Junia Valente, Mustafa Faisal, Justin Ruths, Richard Candell, and Henrik Sandberg, 2016, “Limiting the Impact of Stealthy Attacks in ICS”. In Proceedings of the 23rd ACM Conference on Computer and Communications Security (pp. 1092-1105).
  • Mustafa Faisal, Alvaro Cárdenas, and Avishai Wool. "Modeling Modbus TCP for Intrusion Detection." In International Workshop on Cyber-Physical Systems Security (CPS-Sec), 2016.

Patent:

Publication number: 20170082666

Abstract: According to some embodiments, the present disclosure may relate to a method that includes receiving an energy consumption trace representing energy usage over time that is sampled at a sampling interval. The method may also include parsing the energy consumption trace into one or more segments using change point detection, and selecting one or more of the one or more segments as a representative always-on load segment based on one or more of the following: a lowest average and a minimum duration. The method may also include determining a periodic always-on load based on the representative always-on load segment and the sampling interval. The present disclosure may also relate to associated systems and devices.

Type: Application

Filed: September 17, 2015

Publication date: March 23, 2017

Inventors: Daisuke MASHIMA, Mustafa FAISAL

Talk(s):

    • Issues about Modeling of Modbus/TCP for Intrusion Detection Systems in SCADA networks, UKC 2016, Hyatt Regency DFW Airport, Dallas, TX