About
Last updated: October 2026
Hi, I'm Maryam, a computer scientist in Toronto working toward graduate research in trustworthy AI and ML security. This site is where I document what I'm building and learning along the way.
I studied computer science (with a math minor) at the University of Toronto, and spent about a year afterward as a software engineer. I mostly worked on backend systems, data pipelines, and compliance-focused tooling, though working in a start-up setting meant learning to wear many different hats.
These days I'm back at U of T as a research intern in the CleverHans Lab, supervised by Nicolas Papernot. I'm working on privacy in multi-agent LLM systems: whether agents acting on users' behalf can do their work without leaking sensitive information to unintended recipients.
I'm also part of a research team on harmful fine-tuning through SPAR (the Supervised Program for Alignment Research), looking at how a small fine-tune strips a language model's safety training, and how to harden models against it or detect that it happened.
Rooted in empirical research, both projects align with my passion for building, experimenting, and stress-testing models.
On the side, I enjoy walking, learning about random topics, and watching anime. I'm currently learning French; or at least doing my best to try.