Representation Learning in Knowledge Graphs

Mastercard is looking to make transactions simple and secure for its customers and vendors across the globe by harnessing the power of graph learning. In this project, the power of graph-based deep learning will be utilized to develop a system that can detect fraud entities, anomalous communities, etc. This track will enable card users and […]

Read More
Boosting Robustness of Deep Neural Networks against Sparsity-aware Adversarial Attacks

Over the past few years, deep neural networks (DNNs) have been used to solve a wide range of real-life problems. However, DNNs are vulnerable to adversarial attacks where carefully crafted input perturbations can mislead a well-trained DNN to produce false results. As DNNs are being deployed into security-sensitive applications such as autonomous driving, adversarial attacks […]

Read More
Personalization of Web Tasking

A web task is defined as the set of services, sessions, and sequence of interactions that are required to perform a certain user objective. The current Web tasking model does not consider user preferences and context when executing a Web task. The proposed research project aims to improve the experience of Web users through personalization […]

Read More
Petroglyph Complexes of the Upper Indus in Northern Pakistan – Digital Annotation of Visual Cultural Heritage

Complex sites with concentrations of inscriptions and rock drawings (petroglyphs) in the Upper Indus region in northern Pakistan are threatened with inundation in a flood zone of Diamer-Basha dam. These invaluable cultural heritage resources comprising over 30,000 petroglyphs and approximately 4000 inscriptions abraded into the desert varnish on the surfaces of rocks at dozens of […]

Read More
Mutual avoidance behaviors of previously-concussed athletes passing through a doorway

The proposed study will extend the findings of the current literature through the following objectives: 1) to understand individual’s ability to use visual information to accurately avoid an approaching person; 2) determine the role of environmental objects (i.e., doorway) in regulating avoidance behaviours; and 3) determine any concussion-related avoidance behaviour changes. To meet these objectives, […]

Read More
AI to increase statistical power in clinical neuroimaging

Many studies worldwide use neuroimaging to investigate whether there are abnormalities in the structure or function of the brain that underlie mental disorders. The sample sizes in these studies are limited because of the high cost of neuroimaging and difficulties in recruiting large numbers of patients if the disease is rare. This is a problem […]

Read More
AI For Real-Time Embedded Applications: Honeypot Learning and Predicting for OoD Attack Patterns

Today’s automobile is more than a mechanical tool; it contains a myriad of computers, sensors, IoT, and embedded nodes. The embedded system is the heart of a vehicle’s electronic system because of its versatility and flexibility. Furthermore, these systems are becoming increasingly sophisticated and interconnected, both to each other and to the Internet. However, with […]

Read More
Gamification of Neurorehabilitation-Centric Hand Exercises Post Stroke or Brain Injury

Stroke is the number one cause of adult disability in the world. Due to the neurological damage from stroke, a vast majority of individuals suffer from hand function disability (~70%). To improve hand function and overcome challenges from this disability, IRegained has developed the MyHandTM system, a connected mechatronic device with programmed proprietary hand function […]

Read More
Tiresias: Client Private Malware Protection

Tiresias is a client private solution to malware protection and threat intelligence. Tiresias allows a user to put all their incoming files in a cryptographically secure Data Chest locally. After sending the Data Chest to our cloud environment, our AI scans and infers if it is malicious without seeing the actual file content from the […]

Read More
Deformation Behavior and Fatigue Failure Analysis of Functionally Graded B4C Particle Reinforced Aluminum Alloy-Based Metal Matrix Composite

The proposed work under this award program involves fabrication of functionally graded B4C particle reinforced AA6061 metal matrix composite through stir-centrifugal casting technique. Subsequently, the deformation behavior and fatigue failure analysis of the fabricated composite will be carried out. The 2D microstructure, constituent phases, particle distribution, and gradient will be revealed by light and electron […]

Read More
Migration, Belonging and the Politics of Local Development in Eastern Nigeria

The proposed doctoral research aims to use Igbo Hometown Associations in Nigeria as a context to explore identity-based associational groups that operate locally but with ties to transnational migration dynamics and their diaspora. Specifically, it will examine how these ties enable their acting as non-state governance actors that self-organize to provide public goods, despite weakness […]

Read More