세미나

산업공학과에서는 최신 연구 트렌드를 공유하고 학문적 통찰을 나누는 연구세미나를 개최합니다.

혁신적인 연구에 관심 있는 학부생, 대학원생 여러분의 많은 참여를 환영합니다!

 

📅 세미나 정보

🔸일시 : 2025년 6월 11일(수) 13:00

🔸장소 :  112동 2층 화상회의실(Conference Room)

🔸발표자 :  Ph.D Jinseong Park(KIAS)

🔸강연주제: How Can We Ensure Privacy of Training Data in Deep Learning Models?

  – This seminar will be conducted in English

 🔸Zoom: https://unist-ac-kr.zoom.us/j/87817004403?pwd=DXIjyRa7SEhZ8Pca1QpCcmE7gwazIa.1

ID:878 1700 4403

PW: unist1234

 

📑ABSTRACT: Deep learning models are known to pose a risk of privacy leakage from training data samples. To safeguard against potential data exposure, various methods, such as anonymization and encryption, have been proposed. Among them, differential privacy (DP) offers a mathematical guarantee against adversaries with practical implementations in training neural networks through gradient modifications. However, training deep learning models with DP may lead to a degradation in prediction performance compared to models without DP. In this talk, we will review recent advancements in privacy-preserving deep learning models, particularly focusing on the recent evolution of generative models. We will end with a discussion on promising future directions in the field.

 

👤Bio: Jinseong Park is an AI research fellow at the Center for AI and Natural Sciences (CAINS) of the Korea Institute for Advanced Study (KIAS). He received his B.S. degree in Industrial and Management Engineering from the Pohang University of Science and Technology (POSTECH), and his M.S. and Ph.D. degrees in Industrial Engineering from Seoul National University in February 2025. His research interests include the safety and privacy of machine learning and time series analysis.