cv
Basics
Name | Younghan Lee |
Label | Postdoctoral Researcher |
201younghanlee@gmail.com | |
Phone | (+82)10-9103-5353 |
Url | https://201younghanlee.github.io |
Summary | Ph.D. from Seoul National University who is interested in Security and Privacy in Artificial Intelligence |
Work
- 2024 - Present
Postdoctoral Researcher
SOR Lab, Seoul National University
Research interests include Security and Privacy in Artificial Intelligence
- 2024 - Present
Lecturer
Department of Convergence Security Engineering, Sungshin Women's University
Teaching Machine Learning-based Communication Networks Security
- 2024 - Present
Education
Publications
-
2023 Exploring Clustered Federated Learning’s Vulnerability against Property Inference Attack
Proceedings of the 26th International Symposium on Research in Attacks, Intrusions and Defenses
In this paper, we explore the potential risk of unintended property leakage in Clustered Federated Learning (CFL) by subjecting it to both passive and active Property Inference Attacks (PIAs).
-
2023 FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models
European Symposium on Research in Computer Security (ESORICS)
In this work, we propose FLGuard, a novel byzantine-robust FL method that detects malicious clients and discards malicious local updates by utilizing the contrastive learning technique, which showed a tremendous improvement as a self-supervised learning method.
-
2022 A Pilot Study of Machine Learning–Based Algorithms to Assist Integrated Care for Older Community-Dwelling Adults
CIN: Computers, Informatics, Nursing
Our study aims to explore the possibility of implementing machine learning decision-support algorithms in the integrated care of older community-dwelling adults.
-
2022 Precise extraction of deep learning models via side-channel attacks on edge/endpoint devices
European Symposium on Research in Computer Security (ESORICS)
Our work provides a comprehensive understanding of such a relationship for the first time and would benefit future MEA studies in both offensive and defensive sides in that they may learn which pieces of information exposed by SCA are more important than the others.
-
2021 Learn2Evade: Learning-based generative model for evading PDF malware classifiers
IEEE Transactions on Artificial Intelligence
We propose a variant of generative adversarial networks that generate evasive variant PDF malware (without any crash), which can be classified as benign by various existing classifiers yet maintaining the original malicious behavior.
-
2020 Hawkware: network intrusion detection based on behavior analysis with ANNs on an IoT device
ACM/IEEE Design Automation Conference (DAC)
In this paper, we propose a novel IDS named Hawkware, a lightweight ANN-based distributed NIDS that runs on an IoT device and analyzes the device's runtime behavior in tandem with its network traffic.
-
2019 Riskim: Toward complete kernel protection with hardware support
Design, Automation & Test in Europe Conference & Exhibition (DATE)
In this paper, we introduce RiskiM, our new hardware-based monitoring platform to ensure kernel integrity from outside the host system.
-
2018 Mimicry resilient program behavior modeling with LSTM based branch models
Deep Learning and Security Workshop (DLS 2018)
In this paper, we report our preliminary findings in our research to build a mimicry resilient program behavior model that has lesser drawbacks.
Projects
- 2024 - Present
Motion Tracking System for the Analysis of the Activity and Emotional Patterns of Pets with Deep Learning
- Seoul National University (SNU)
- 2023 - Present
Development of Artificial Intelligence-based Phishing Attack Prevention and Performance Verification Technology
- Seoul Business Agency (SBA)
- 2022 - Present
- 2022 - Present
Research on Applying Artificial Intelligence on Medical Data
- Ewha Womans University Medical Center (EUMC)
- 2023 - 2023
- 2023 - 2023
- 2019 - 2021
Research on Applying Machine Learning on Health and Nursing Data
- Seoul National University Hospital (SNUH)
- 2019 - 2020
Development of Intelligent Security Threat Countermeasure Solution based on Aritificial Intelligence
- Seoul Business Agency (SBA)
- 2017 - 2020
Development of Programmable IPs and Unified SDK to Enable Building Security-Integrated Computer Systems
- Ministry of Science and ICT
- 2017 - 2019
Development of Cloud-based Intelligent Security Technology for Providing Customized Security Services
- Ministry of Science and ICT
- 2016 - 2017
Development of Network Anomaly Detection
- SK Infosec
Skills
Programming | |
Python | |
C | |
MATLAB |
AI Tools | |
Pytorch | |
Tensorflow | |
Keras | |
scikit-learn |
Languages
Korean | |
Native speaker |
English | |
Fluent |
Interests
Research in Security and Privacy | |
Security and Privacy in AI | |
Adversarial Example Attacks | |
Model Extraction Attacks | |
Differential Privacy |
Research in Deep Learning | |
Federated Learning | |
Differential Privacy | |
Multimodal Learning |
Research in Robotics | |
Robotics | |
Motion Capture | |
Sensors |