Skip to main content
Ontario Tech acknowledges the lands and people of the Mississaugas of Scugog Island First Nation.

We are thankful to be welcome on these lands in friendship. The lands we are situated on are covered by the Williams Treaties and are the traditional territory of the Mississaugas, a branch of the greater Anishinaabeg Nation, including Algonquin, Ojibway, Odawa and Pottawatomi. These lands remain home to many Indigenous nations and peoples.

We acknowledge this land out of respect for the Indigenous nations who have cared for Turtle Island, also called North America, from before the arrival of settler peoples until this day. Most importantly, we acknowledge that the history of these lands has been tainted by poor treatment and a lack of friendship with the First Nations who call them home.

This history is something we are all affected by because we are all treaty people in Canada. We all have a shared history to reflect on, and each of us is affected by this history in different ways. Our past defines our present, but if we move forward as friends and allies, then it does not have to define our future.

Learn more about Indigenous Education and Cultural Services

ANTS Projects

Current Projects

  • Artificial Intelligence, Machine Learning and Privacy: From Threats to Solutions

    Principal Investigator: Khalil El-Khatib

    Artificial intelligence (AI) is one of several modern approaches to achieve human-equivalent machine intelligence [[i]]. It is described as a field of study focused on creating intelligent entities, with numerous applications in various domains including security, commerce, and intelligent transportation system. Machine learning (ML) is a tool to help create and implement artificial intelligence systems, and leans heavily onto statistical methods to accomplish its goals. While an artificial intelligence system may perceive its environment with sensors and take actions with actuators, machine learning enables the system to learn from data collected from these sensors. Despite the fact that there are numerous perceived benefits for developing human-equivalent machine intelligence, such as fostering the rapid development of human technological advancement, there are also a number of public concerns about the technology ranging from economic instability to apocalyptic. The project will explore known privacy risks associated with artificial intelligence and machine learning, identify popular use cases and create a venue to discuss their privacy associated risks.

     

    [i].    N. Bostrom, “Superintelligence: Paths, dangers, strategies. 2014.”

  • MAVIDS: An Intelligent Intrusion Detection System for Autonomous Unmanned Aerial Vehicles

    Principal Investigator: Khalil El-Khatib

    Unmanned Aerial Vehicles (UAVs) have proven to be a useful technology in numerous industries including industrial control systems surveillance, law enforcement, and military operations. Due to their heavy reliance on wireless protocols and hostile operating environments, UAVs face a large threat landscape. As attacks against UAVs increase, an intelligent Intrusion Detection System (IDS) is needed to aid the UAV in identifying attacks. The UAV domain presents unique challenges for intelligent IDS development, such as the variety of sensors, communication protocols, UAV platforms, control configurations, and dataset availability. A novelty-based approach to intrusion detection in UAVs is proposed by using one-class classifiers, exploiting the use of flight logs for training. The proposed technique is integrated into a fully developed IDS which operates onboard the UAV, allowing it to detect and prevent attacks even when communication to the ground control station is lost.

  • Cybersecurity Testing of Connected and Autonomous Vehicles

    Principal Investigator: Khalil El-Khatib

    Connected and Autonomous Vehicles (CAVs) are disrupting the automotive and transportation industry and introducing rapid technological evolution. The benefits and possibilities with connected and autonomous vehicles are plentiful, however they are not without risk. The speed of innovation and adoption of CAV technologies must be complemented by comprehensive and robust testing to ensure the safety of the vehicles passengers and data. In this project, we address the concern of cybersecurity testing for CAVs.

  • AI-based framework for polymorphic network attack and defence

    Principal Investigator: Shahram S. Heydari

    Description: The objective of this research project is to develop techniques based on adversarial machine learning techniques  for detecting polymorphic anomalies; i.e. anomalies that dynamically change their profile. In recent years, the use of Artificial Intelligence (AI) in cybersecurity has attracted significant attention, with both attackers and defenders deploying AI-based techniques against each other to successfully attack or defend cyber resources. Our initial research results show that when an attacker deploys AI to change its attack profile, most current techniques fail to correctly classify and distinguish between malicious and normal traffic. We are investigating the use of various Machine Learning and Deep Learning techniques in a Generative Adversarial Network (GAN) for improving the success rate of cyberdefence systems in not only detecting the malicious traffic, but also avoiding false positives; i.e. mislabeling normal traffic as malicious; thus improving the network utilization along with maintaining the integrity and security of the cyber physical systems.

  • Vehicular Sensing Platform for Smart Cities

    Principal Investigator: Richard W. Pazzi

    Supported by: NSERC, NorthLine Canada

    As Ontario’s population grows, traffic management becomes even more challenging. Tracking down elements of traffic flow such as vehicle type, congestion and traffic patterns, and vehicle speed adds immense value to effectively managing traffic as well as making policy decisions. The proper management of the additional cost, however, requires the deployment of advanced automated traffic management solutions.

    The industry partner in this project is  NorthLine Canada, a national provider of vehicle detection systems. The company has recently been interested in updating some of its vehicular detection systems by incorporating into them new features and investigating the benefits of integrating these new systems with IOT solutions. The data collected from the vehicle detection systems provide insight, which is quite valuable in relieving traffic congestion, detecting types of vehicles passing through an intersection and statistically demonstrating the detailed traffic flow of vehicles at important intersections.

    This is an ongoing short-term project that aims at implementing a vehicular detection system and the underlying routing algorithms and software management platforms. The hardware for this project will be implemented with the help of North Line Canada. The research work will include designing the embedded firmware for the sensor motes, implementing the routing algorithms to send data to a common hub and designing the software management system on the gateway responsible for data analytics and presentation. This project also provides training and hands‐on‐experience for undergraduate and graduate students and research assistants in the field of vehicular detection, vehicular mobility modeling, simulation and performance analysis, thereby enhancing Canada’s HQP significantly in an area of technology that is becoming more and more attractive.

    This initial NSERC ENGAGE project will build the platform and underlying communication protocols. Later, we will develop a mesh network algorithm to make better use of the batteries in those devices while gathering data from vehicles. Maintenance costs can be reduced if we succeed in extending battery lifetime by implementing smart algorithms, due to the longer battery replacement intervals.  The plan is to apply for an NSERC Collaborative Research and Development Grant (CRD) to continue the project with the industry partner.

  • NexGenDFA: A Framework for Next Generation Digital Forensic Analysis

    Principal Investigator: Khalil El-Khatib

    Supported by: NSERC

    With the spike in the number and scale of cyberattacks, digital forensic (DF) has become an indispensable tool for security experts. Cyberattacks are costing businesses trillions of dollars, and the loss of billions of personal and financial records (and possible meddling with elections). Executing digital forensics after a security incident becomes a necessity to identify root causes and possibly individuals behind the attack. It can also help to avoid future similar incidents, and when possible, accelerate the restoration of any service affected. However, digital forensics is becoming a very complex and overwhelming task due to a number of reasons including; (1) the large number of data sources of forensic interest and sometimes in proprietary formats, (2) the enormous volume of forensic data, and last but not least, (3) the association of new technologies in cyberattacks (Blockchain, Internet of Things (IoT), Connected and Autonomous Vehicles, Drones, and cloud/edge/fog computing). These all add convolution to the processes of digital evidence acquisition, triage and analysis. In this research program, I propose to investigate the design and implementation of a forensic framework and associated tools that use machine learning algorithms combined with big data visual analytics that go beyond the current state of the art of forensic tools. The outcome of the program will help cut the time and cost for digital forensic investigations, by providing digital forensic analyst with the knowledge and tools to better unveil, understand and connect digital evidences. Additionally, the program will address real-world data analytic problem leading to enormous social and economic benefits for Canada. Last but not least, the research program will also contribute to the development of research talents and the training of HQP in machine learning and visual analytics, positioning Canada as a leader in these fields.

  • Applications of Reinforcement Learning in Networking

    Principal Investigator: Shahram S. Heydari

    Description: The main objective of this project is to utilize Reinforcement Learning (RL) methods for a variety of network control functions such as optimal routing, congestion control and quality of service, in a software-defined network environment. The vision of this project is that of an AI-managed SDN where specialized AI modules handle the task of dynamically optimizing network operations to achieve the desired target performance metrics.

  • Optimal Content Delivery over Software-Defined Wide Area Networks

    Principal Investigator: Shahram S. Heydari

    Supported by: NSERC, Ericsson Canada

    Summary: The main focus of this project is on improving the performance of cloud-based content delivery networks (CCDN), in particular based on novel functionalities that software-defined networking and network function virtualization brings to such networks. Our objective is to develop and validate methods for optimal network service provisioning in multimedia streaming networks that are operating on top of such software-defined virtualized infrastructures. Our research includes developing techniques to measure and collect quality of experience (QoE) information from end users, formulating and solving complex resource optimization problems in the cloud, and conducting large-scale simulations to evaluate various algorithms for  resource allocation in cloud networks. More recently we have started researching the capabilities of Fog computing in collecting QoE analytics and optimal resource allocation decisions.

  • Social Network-based Data Dissemination in Vehicular Sensor Networks

    Principal Investigator: Richard Pazzi

    Summary-The convergence of vehicle and sensor networks offers viable means for data dissemination to distributed services such as traffic monitoring, safety warnings, infotainment, and proactive surveillance of roads and streets. However, data dissemination in vehicular sensor networks (VSNs) is a challenging task due to high mobility of vehicles; frequent network topology changes; high volume of data; and different data dissemination and application requirements. For instance, most safety warning applications will require fast and reliable data delivery to nearby vehicles, which can be achieved by local broadcasts. A monitoring service may require continuous data delivery to a region or command centre, in which the use of broadcasts would not be feasible or efficient. Thus, another challenge lies in adapting on-the-fly to the best data dissemination approach depending on the different vehicle or user's interests.
    Existing solutions address some of these issues individually and do not adapt to different services or user requirements. The heterogeneity of services, users and data requirements seems to be an opportunity to apply social network-based decision making when selecting forwarding vehicles. It might be possible to map mobility patterns as close as possible to real traffic behavior by exploiting social ties among drivers. Such mapping would be extremely useful in data forwarding decisions. Therefore, this research program will investigate these issues under a unified framework and then develop novel hybrid adaptive techniques that take advantage of the strengths and deal with the weaknesses of existing data dissemination strategies. This program will focus in devising social network-based schemes that exploit "interactions" among vehicles (i.e., common visited places, encounters, mobility patterns) as well as drivers' social ties to improve data dissemination in VSNs. It is expected that the proposed program will not only foster advances in VSNs and intelligent transportation systems (ITS), but also prepare students in this demanding research field and place them in a more competitive position in the academia and industry.


Selected Past Projects

  • Predictive Cybersecurity Architecture
    Principal Investigator: Shahram S. Heydari (2018 - 2019)

    Supported by: NSERC, Telus

    The key objective of this project is to develop a probabilistic predictive model of security attacks for telecommunication networks. Such predictive models can be used to develop a proactive strategy of confronting large scale network security attacks in real-time. In this approach, as the attack against the network infrastructure unfolds, a prediction engine will analyze the incoming data in real-time and with the use of historic data, will predict the next stage of the attack and implements the best course of action (for instance by redirecting traffic flows through a software-defined network controller API). In order to take such proactive approach, probabilistic models of attacks are required, which is the main subject of this research. We will also study the feasibility of using AI techniques to exploit these models for threat monitoring, prediction, and secure decision making.
  • Risk Assessment of SkyX: Advanced Autonomous Drone Platform for Monitoring Critical Infrastructures

    Principal Investigator: Khalil El-Khatib

    The use of drones today is exploding. By 2020, the Federal Aviation Administration
    (FAA) expects the number of drones in the US to rise to 7 million, making it a $13 billion dollar industry. Along with this momentum is the adoption of drones for commercial and military applications. More than 600,000 drones are expected to be registered for commercial use by 2020. As drones are being used more and more, their uses are also growing. Gone are the days of drones simply taking photos. Modern drones are being used across industries in much more critical commercial applications including the inspection of oil and gas pipelines, law enforcement, emergency management, medical supply delivery, and of course military intelligence and payload delivery. The goal of the work will be to audit the current systems and methods, identify potential flaws and attack vectors and propose potential solutions to solve the problems.  

  • Protecting Critical Infrastructure against Large-Scale Failures and Attacks

    Principal Investigator: Shahram S. Heydari (2010-2015)

    Supported by: NSERC, Ericsson Canada

    Summary: The main objectives of this research was to analyze the impact of large scale failure scenarios arising from security attacks or natural disasters on the telecommunication infrastructure, and to design multi-layer restoration schemes, methods and algorithms for integrated protection and traffic restoration of access, metropolitan and backbone layers of the network. Survivable topology design, cost analysis, and administrative and management issues related to large-scale failure recovery in the communication infrastructure are among the topics that were targeted in this research program. Over the years we have studied methods for improving the survivability of optical and LTE networks backbones, and proposed an SDN-based controller design for preventive failure management in communication networks. This design has been patented (US patent# 9,590,892), and we are currently looking for partners to commercialize it. We also formulated an optimized solution for SDN switch operations in failure recovery scenarios.

  • Securing the Next-Generation Smart Electric Grid

    Principal Investigator: Khalil El-Khatib (2010-2015)

    Summary-Recent advances in electronic and communication technologies have enabled the development of miniature computing nodes with wireless communication capability. These nodes can communicate with each other over wireless channels, and in the absence of an existing infrastructure, autonomously organize themselves to form small- or large-scale wireless networks. One of the domains that directly benefits from advances in wireless communication networks is the electric grid: old meters are being replaced with smart meters that allow energy providers to continuously and remotely collect, monitor, and provision energy consumption and distribution. Building the smart grid infrastructure with two-way communication of data consumption, monitoring and control, requires ultimate consideration of many security and privacy issues. As the infrastructure is expected to be very complex, with multiple entry points, and to connect an extremely large number of communication devices with various communication, computation, and storage capabilities, there is definitely a high risk that an attack on the infrastructure can have a drastic effect on the safety and well being of large number of people. Additionally, an ongoing monitoring of energy consumption by utility providers can be highly intrusive and can reveal information about the activities of consumers inside their homes. The objective of this research program is to build secure communication networks for the smart grid with trusted and authentic data and devices, and which allows the utility providers to reliably provision the grid without jeopardizing the privacy of the consumers.

  • Mobile Wireless Sensor Network Localization and Visualization

    Principal Investigator: Shahram S. Heydari (2010-2012)

    Supported by: NSERC, Fed Dev, Solana Networks

    Summary: The objective of this project was to evaluate and propose the most suitable methods for location discovery and visualization of tactical mobile ad-hoc network environments. We proposed a high level design for a visualization tool based on an OLSR routed network, developed a predictive filtering technique for adjacency-based localization in MANETs, and created a simulation environment for performance evaluation of the data collection, visualization and routing algorithms in this scenario.