Sunjun Hwang
AI & Quantum Computing Researcher
Building Robust AI Systems that Work in the Real World
01. About Me
I'm a researcher passionate about pushing the boundaries of Artificial Intelligence and Quantum Computing at Yonsei University's RAISE Lab.
Research Direction
I focus on making AI systems more robust and reliable — from quantum-enhanced machine learning to safety-critical applications in autonomous driving and semiconductor design.
Problems I Care About
How do we build AI that doesn't break under uncertainty? How can quantum computing accelerate what classical methods can't? These are the questions that drive my work every day.
What's Next
Pursuing graduate research at the intersection of quantum computing and trustworthy AI, aiming to bridge theory and real-world deployment.
"When something is important enough, you do it even if the odds are not in your favor."
— Elon Musk
02. Research Areas
Quantum Computer
Exploring quantum algorithms and hybrid quantum-classical systems for real-world applications.
Artificial Intelligence
Deep learning, federated learning, and adversarial robustness in neural networks.
Autonomous Vehicle
Simulation and development of autonomous driving systems using CARLA and reinforcement learning.
AI Security
Adversarial attacks, defense mechanisms, and robustness analysis for AI systems.
03. News
Our Paper, "Functional Recovery of Deep Neural Networks via Logit-Based External Calibration" has been accepted to KICS
Our Paper, "Adversarial Robustness Analysis of Deep Learning-Based Automatic Modulation Classification in Wireless Communication" has been accepted to ICAIIC IEEE 2026
Our Paper, "Design and Implementation of an FPGA-Based Real-Time Voice Risk Detection System" has been accepted to KCS 2026
Our Paper, "Quantum-Secured Hybrid Communication System for Tactical Military Networks: Implementation and Performance Analysis of BB84 Protocol Based on Penny Lane" has been accepted to JKICS 2026
Our Paper, "Quantum Noise-based Adversarial Attack on Diffusion Models and Analysis of Defense Mechanisms" has been accepted to KIIT-JICS 2026
Our Paper, "Logit-based Knowledge Distillation for Heterogeneous Medical Image Federated Learning" has been accepted to KIIT Conference
Our Paper, "Post-hoc Defense with Knowledge Distillation in Federated Learning: An Empirical Study against FGSM and PGD Attacks" has been accepted to KICS Conference
Our Paper, "Classification of Pneumonia in Chest X-rays Using a Hybrid Neural Network Based on a 3-Qubit Quantum Circuit" has been accepted to KSLI Conference
Our Paper, "Performance Comparison of Deep Learning Models for Seismic Signal Denoising" has been accepted to KIIT Conference
Our Paper, "A Study on Robustness Enhancement and Multi-Adversarial Attacks in Vision Transformer-based Image Classification Models" has been accepted to KIIT Conference
04. Get in Touch
If you are interested in quantum computing technology, computer vision technology, deep learning technology, or web programming, please feel free to contact me via email.
Supported by Yonsei University, RAISE Lab
Say Hello