Sara Saeidian

I am a postdoctoral researcher at KTH Royal Institute of Technology, supported by a Swedish Research Council (VR) International Postdoctoral Fellowship. As part of the fellowship, I am conducting my research at the Comète team at Inria Saclay in France. 

My research focuses on the theoretical foundations of trustworthy machine learning, with a particular focus on privacy and algorithmic fairness. I am especially interested in developing mathematically rigorous frameworks for analyzing the privacy and fairness guarantees of algorithms, and in understanding the fundamental trade-offs between these properties.

I received my PhD in February 2024 from KTH Royal Institute of Technology. During my doctoral studies, I introduced pointwise maximal leakage (PML), a new privacy measure within the family of quantitative information flow definitions. PML is provably more general than differential privacy, and offers a robust and flexible theoretical framework for reasoning about information leakage. My current research builds on my PhD work by developing more theoretical tools within the PML framework.