Sara Saeidian
I am a postdoctoral researcher at KTH Royal Institute of Technology. My research focuses on developing privacy-preserving frameworks in statistics and machine learning, often leveraging techniques from information theory.
I received my PhD in February 2024 from KTH. During my PhD, I introduced Pointwise Maximal Leakage (PML), a novel privacy measure that extends both differential privacy and quantitative information flow. PML is operationally meaningful, robust, and flexible. Currently, my research focuses on applying PML to various problems in statistics and learning.
news
| Nov 04, 2024 | Our paper Rethinking Disclosure Prevention with Pointwise Maximal Leakage has been accepted to the Journal of Privacy and Confidentiality. |
|---|---|
| Oct 17, 2024 | My very first public appearance!  I was invited to speak at Digitalize in Stockholm 2024, one of Sweden’s premier tech events which is open to the public. I participated in the panel “To Legislate or Not to Legislate the AI Realm” and shared my thoughts on the newly implemented AI Act and its impacts on reseach, innovation, and soceity. |
| Sep 10, 2024 | Our paper Extremal Mechanisms for Pointwise Maximal Leakage has been published in IEEE Transactions on Information Forensics and Security. |
| Sep 05, 2024 | I presented our paper Evaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage at the 2024 Annual Privacy Forum. |