Introduction to Differential Privacy
Pasin Manurangsi Google Research
Course Summary |
About the lecturer |
Location and schedule |
As data analytics and machine learning increasingly drive decision-making, the risk of exposing sensitive individual information grows alongside them. Traditional anonymization techniques often fall short of mitigating these risks. Differential privacy instead offers a mathematically rigorous framework for privacy-preserving algorithms, providing formal privacy protection. In this lecture series, we will discuss the foundations of differential privacy, covering its formal definition, core properties, basic algorithmic mechanisms, and theoretical lower bounds.
About the lecturer:Pasin Manurangsi is a staff research scientist at Google Research. He works primarily on privacy-preserving algorithms, hardness of approximation, and computational social choice. He received his PhD from UC Berkeley in May 2019 co-advised by Prof. Luca Trevisan and Prof. Prasad Raghavendra, and bachelor's and master's degrees from MIT in January 2015 under the supervision of Prof. Dana Moshkovitz. Pasin received the Danny Lewin best student paper award at STOC 2017, the best student paper award at ALT 2021, and the best paper awards at WAOA 2021 and FORC 2026. He has served on several program committees, including co-chairing the PETS 2023-24 artifact review committee; he was also selected as a distinguished SPC at IJCAI 2021 and a distinguished PC at IJCAI 2023.
Location and schedule:
|
|
|
||||||||||||||||