Musa Taib
Incoming PhD Student (starting January 2027), Electrical and Software Engineering, University of Calgary
Secure Agentic AI, Privacy-Preserving Federated Learning
Biography
Musa Taib will join DENOS Lab as a PhD student in January 2027. He completed his MSc in Electrical Engineering at the University of Calgary, where his research applied AI to confidential mental health and social services data.
After his MSc, Musa worked with DENOS Lab to develop a privacy-preserving federated learning framework that allowed multiple Calgary agencies to train a shared model for predicting homelessness risk without sharing their sensitive client records. The work was published at the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2024).
His doctoral research will focus on the secure deployment of agentic AI. As AI systems increasingly act as autonomous agents that use tools, interact with live systems and carry out tasks over several steps, security concerns extend beyond protecting data to the actions these agents can take. Musa’s work will examine both sides of this problem, protecting AI agents from manipulation and misuse, and protecting the systems and resources they interact with from being exploited through those agents.
Projects
-
Secure deployment of agentic AI
Protecting AI agents from manipulation and misuse, and protecting the systems and resources they act on from being exploited through those agents.
-
Equitable AI for housing and homelessness
Privacy-preserving federated learning that lets Calgary agencies train a shared homelessness risk model without sharing sensitive client records.
Publications
- AAAI/ACM AIES2024
Enhancing Equitable Access to AI in Housing and Homelessness System of Care through Federated Learning