Hello! I am a Researcher at Mila working at Gauthier Gidel's lab. I recently completed my master's at Université de Montréal and Mila under the supervision of Gauthier Gidel and Ioannis Mitliagkas. During my studies, I spent some time at ServiceNow Research as a Visiting Researcher, where I worked with João Monteiro and Valentina Zantedeschi. Prior to coming to Montreal, I received my bachelor's degree at Sharif University of Technology in Computer Science.
I am interested in the fundamentals of machine learning, where I can explore how AI can be used effectively and efficiently to improve decision-making across various domains. My research has evolved from studying predictive models that actively shape the environments they're designed to analyze to improving inference optimization techniques that balance computational efficiency with performance. Most recently, my focus has shifted to uncovering hidden vulnerabilities in large language models and how to make them more robust.
If there's anything you'd like to discuss with me, you can reach me at: mehrnaz (dot) mofakhami [at] mila.quebec
I wrote this short tutorial while I was a TA in the AI course at Sharif University of Technology. It is an introduction to the main topics in robust and trustworthy ML, including evasion and poisoning attacks, and mechanisms to defend against them.
This scribe note is based on the lectures of Professor Gauthier Gidel in Adversarial Machine Learning course , Winter 2022.
Program Committee Member
Conference and Workshop Reviewer