Hadis Karimipour

Headshot of Hadis Karimipour
Assistant Professor
School of Engineering
Email: 
hkarimi@uoguelph.ca
Phone number: 
(519) 824-4126 ext. 52506
Office: 
THRN 2409
Seeking academic or industry partnerships in the area(s) of: 
Smart Grid Monitoring and Security, IoT/oT security, Machine Learning/Deep learning, Anomaly/fault Detection in Critical Infrastructure
Available positions for grads/undergrads/postdoctoral fellows: 
Please see Karimipour’s website for details about open positions.

Education and Employment Background

Dr. Hadis Karimipour received her PhD in Electrical Engineering from the University of Alberta in 2016. Between 2016 and 2017, she held a position as a postdoctoral fellow at the University of Calgary. She joined the School of Engineering at the University of Guelph in 2017 where she is currently an Assistant Professor and the director of the Smart Cyber-physical System (SCPS) lab.


Research Themes

Today’s critical infrastructures are undergoing a digital transformation with increasing dependency on Internet of Things (IoT) and communication networks, which turns them into highly complex Cyber Physical Systems (CPS).  Although the integration of Information Technology (IT) in CPS improves efficiency, reliability, and sustainability, it links more and more security vulnerabilities to CPS. Dr. Karimipour’s long-term research goal is to develop fully automated intelligent systems for cyber-attack detection, identification and elimination in CPS. Her research group seeks to advance the use of machine learning and Artificial Intelligent (AI) on monitoring and security problems in complex CPS and IoT. It includes developing AI-enabled cybersecurity solutions/ anomaly detection to overcome the limitations of traditional detectors such as low accuracy and slow response rate.  Key areas of focus include:

  1. Machine Learning and Its Applications. Machine Learning (ML) is a subset of Artificial Intelligence (AI) that provides systems with the ability to automatically learn and improve from experience without being explicitly programmed.  The basic premise of ML is to build algorithms that can receive input data and use statistical analysis to predict an output while updating outputs as new data becomes available. Things like growing volumes and varieties of available data, computational processing that is cheaper and more powerful, and affordable data storage are the main motivations toward machine learning developments. ML can be used for anomaly detection, system monitoring, security analysis, load prediction, load forecasting, etc. in cyber-physical systems. 
  2. Anomaly Detection in Smart CPSs. The deployment of smart technologies in the communication layer brings new challenges for online monitoring and control of the Cyber-Physical Systems (CPS). In addition to the failure of physical infrastructure, CPSs are also sensitive to different anomalies on their communication layer. Examples of CPS include smart grid, autonomous transportation systems, medical monitoring, and autonomous vehicles. AI is a popular technology that has the potential to be leveraged in different aspects of CPS monitoring including anomaly/failure detection. AI/ML can extract patterns of suspicious or anomalous behaviour in the system to predict failure in advance.
  3. AI and IoT Monitoring/Security. Over the last decade, IoT platforms have been developed into a global giant that grabs every aspect of our daily lives. Because of easy accessibility and fast-growing demand for smart devices and networks, IoT is now facing more security challenges than ever before. There are lots of discussions about the role of AI/ML in security-aware design and analysis of IoT devices. AI-based methods can be used to identify various attacks at an early stage as well as providing defensive strategies. Moreover, AI seems to be promising in detecting new attacks using learning skills and handle them intelligently. 
  4. AI-enabeld Smart Grid Analysis. The traditional grid is not scalable enough to provide the world’s future energy requirements. Looking at the big picture, a nationwide effort to completely automate the grid is underway. A smart grid integrates a variety of distributed and renewable energy resources which are tightly coupled with IoT technology. These components provide a vast amount of data to support various applications in the smart grid, such as distributed energy management, generation forecasting, grid monitoring, fault detection, home energy management, etc. Considering the huge amount of data and complexity of the grid,  AI techniques can be applied to automate and further improve the performance of the smart grid.
  5. Smart Framing Security Monitoring. Smart farming also known as precision agriculture is an emerging concept that refers to managing farms using technologies like IoT, robotics, and drones.  Whenever you use technology to create value, it presents an opportunity for cyber criminals to exploit it for evil purposes, and smart farming is not an exception. Even a short interruption in the refrigeration chain or other essential infrastructure for food distribution, or a targeted disruption of a highly time-sensitive process such as harvest, could cause major and long-lasting effects. Research on vulnerability prevention, threat mitigation, and cybersecurity at the design and development level are required to avoid significant economic losses

Highlights

  • Awarded more than 500 CAD research and development grants as project principle/co-principal investigator. 
  • Awarded prestigious Queen Elizabet II scholarship on “Large-scale Cyber-Physical Power System Analysis”. 
  • Associate Editor of IET Smart Grids Journal and Frontiers in Communications and Networks journal since 2020.
  • IEEE Senior Member since 2019.
  • Chair of IEEE Women in Engineering, KW Section since 2017.