Younghan Lee

Bldg. Prime, Rm. 50 7

Sunghin Women's University

Seoul, Korea 02844

I am an assistant professor at Convergence Security Engineering Department, Sungshin Women’s University.
I worked as a postdoctoral researcher at Seoul National University.
I received my Ph.D. in Electrical and Computer Engineering from Seoul National University, where I was advised by Prof. Yunheung Paek in 2024.
I received BEng in Electrical and Electronic Engingeering from Imperial College London in 2016.
My research interests include Trust AI and Security. Adversarial Example Attacks, Model Extraction Attacks, Federated Learning, Differential Privacy, Multimodal Learning.

selected publications

FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models

Younghan Lee, Yungi Cho , Woorim Han , Ho Bae , and Yunheung Paek

In European Symposium on Research in Computer Security , 2023

Bib PDF Slides

@inproceedings{lee2023flguard,
  title = {FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models},
  author = {Lee, Younghan and Cho, Yungi and Han, Woorim and Bae, Ho and Paek, Yunheung},
  booktitle = {European Symposium on Research in Computer Security},
  pages = {65--84},
  year = {2023},
  organization = {Springer},
}

Precise extraction of deep learning models via side-channel attacks on edge/endpoint devices

Younghan Lee, Sohee Jun , Yungi Cho , Woorim Han , Hyungon Moon , and Yunheung Paek

In European Symposium on Research in Computer Security , 2022

Bib PDF Slides

@inproceedings{lee2022precise,
  title = {Precise extraction of deep learning models via side-channel attacks on edge/endpoint devices},
  author = {Lee, Younghan and Jun, Sohee and Cho, Yungi and Han, Woorim and Moon, Hyungon and Paek, Yunheung},
  booktitle = {European Symposium on Research in Computer Security},
  pages = {364--383},
  year = {2022},
  organization = {Springer},
}

Learn2Evade: Learning-based generative model for evading PDF malware classifiers

Ho Bae , Younghan Lee, Yohan Kim , Uiwon Hwang , Sungroh Yoon , and Yunheung Paek

IEEE Transactions on Artificial Intelligence, 2021

First two authors contributed equally to this work (Ho Bae and Younghan Lee)

Bib PDF

@article{bae2021learn2evade,
  title = {Learn2Evade: Learning-based generative model for evading PDF malware classifiers},
  author = {Bae, Ho and Lee, Younghan and Kim, Yohan and Hwang, Uiwon and Yoon, Sungroh and Paek, Yunheung},
  note = {First two authors contributed equally to this work (Ho Bae and Younghan Lee)},
  journal = {IEEE Transactions on Artificial Intelligence},
  volume = {2},
  number = {4},
  pages = {299--313},
  year = {2021},
  publisher = {IEEE},
}