Full Name
Mohammad Yaghini
Job Title
PhD Student at UoT & Vector Institute
Company
CleverHans Lab, Vector Institute, University of Toronto
Speaker Bio
I am a PhD student at the CleverHans Lab under the supervision of Nicolas Papernot at the Vector Institute for Artificial Intelligence and University of Toronto. I am also a Meta PhD Fellow. In 2021-2022, I was also a graduate fellow at the Schwartz Reisman Institute for Technology and Society.
My research interests are in the intersection of machine learning and privacy, and more broadly trustworthy machine learning. In particular, I study problems of model governance.
Recently, I have tackled questions of protecting the intellectual property of ML models through detecting and deterring model extraction (via dataset inference and proofs of learning). As well as, detecting and tackling failures of trustworthiness measures, such as fairwashing, where explainability is abused to justify unfairness.
My research interests are in the intersection of machine learning and privacy, and more broadly trustworthy machine learning. In particular, I study problems of model governance.
Recently, I have tackled questions of protecting the intellectual property of ML models through detecting and deterring model extraction (via dataset inference and proofs of learning). As well as, detecting and tackling failures of trustworthiness measures, such as fairwashing, where explainability is abused to justify unfairness.
