IEEE ITSoc Distinguished Lecturer Tour: Prof. Si-Hyeon Lee, Privacy-Preserving Data Utilization with Differential Privacy

#information-theory #privacy #AI #machine-learning
Share

In today's world, our diverse information is collected through various channels and utilized for a range of purposes, including statistical inference and the development of machine learning models. However, privacy threats continue to emerge, revealing that sensitive personal information can be inferred from statistics or machine learning models. In this tutorial, we introduce differential privacy, a representative privacy protection metric, and explore its applications in machine learning and statistical inference. Furthermore, focusing on distribution estimation, a fundamental problem in statistical inference, we will discuss how classical results from combinatorics can be leveraged to develop communication-efficient differential privacy techniques.


  Date and Time

  Location

  Hosts

  Registration


  • Date: 11 Mar 2025
  • Time: 02:15 PM UTC to 03:30 PM UTC
  • Add_To_Calendar_icon Add Event to Calendar
  • Lund University
  • Klas Anshelms väg 10
  • Lund, Skane lan
  • Sweden
  • Building: E Building
  • Room Number: E:2311
  • Contact Event Host

  • Michael Lentmaier, Lund University, michael.lentmaier@eit.lth.se

  • Co-sponsored by Lund University, Lund, Sweden

  Speakers

Prof. Si-Hyeon Lee of Korea Advanced Institute of Science and Technology (KAIST)

Topic:

Privacy-Preserving Data Utilization with Differential Privacy

In today's world, our diverse information is collected through various channels and utilized for a range of purposes, including statistical inference and the development of machine learning models. However, privacy threats continue to emerge, revealing that sensitive personal information can be inferred from statistics or machine learning models. In this tutorial, we introduce differential privacy, a representative privacy protection metric, and explore its applications in machine learning and statistical inference. Furthermore, focusing on distribution estimation, a fundamental problem in statistical inference, we will discuss how classical results from combinatorics can be leveraged to develop communication-efficient differential privacy techniques.

Biography:

Si-Hyeon Lee received the B.S. (summa cum laude) and Ph.D. degrees in electrical engineering from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2007 and 2013, respectively. She is currently an Associate Professor with the School of Electrical Engineering, KAIST. She was a Postdoctoral Fellow with the Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada, from 2014 to 2016, and an Assistant Professor with the Department of Electrical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea, from 2017 to 2020. Her research interests include information theory, wireless communications, statistical inference, and machine learning. She is currently an IEEE Information Theory Society Distinguished Lecturer (2024-2025). 

 

 

Address:Korea Advanced Institute of Science and Technology (KAIST), , Daejeon, South Korea