👋 Hi, I'm

Hanjin Lee 이한진

AI Security Researcher

Integrated M.S./Ph.D. in Computer Science · AISLab, Yonsei University

I work on understanding, controlling, and securing modern generative models — especially diffusion-based systems — from a principled, mathematical perspective. My goal is AI that is trustworthy, controllable, and secure by design.

Hanjin Lee
📄 papers
🔬 Research

What I work on

Bridging theoretical rigor and practical system reliability — so AI behaves safely even under distribution shift or adversarial conditions.

🌀

Generative Model Safety

Securing and controlling diffusion-based systems with distribution-preserving mechanisms that keep outputs reliable.

DiffusionReliabilityControl
🛡️

Adversarial Robustness

Studying adversarial examples, patches, and perturbations — how they break vision systems, and how to defend against them.

AttacksRobustnessXAI
🔐

AI for Security

Applying ML to malware classification, anomaly detection, and defending models against extraction & inversion attacks.

MalwarePrivacyDetection
📚 Publications

Selected & full publications

Reverse-chronological. Bold marks my name. Peer-reviewed journals, conferences, and preprints.

📰 News

Recent updates

🎓 Education & Experience

Background

Education

2024.03 – now
Yonsei University
Integrated M.S./Ph.D., Computer Science (AI)
2020.03 – 2024.02
Yonsei University, Mirae Campus
B.S. in Computer Engineering

Experience

2024.03 – now
AISLab, Yonsei University
Graduate Researcher — AI security & generative models
2023.03 – 2024.02
AISLab, Yonsei University
Undergraduate Researcher
🏆 Awards & Honors

Recognition

10+ best-paper and presentation awards across Korean AI & signal-processing societies.

2026🏆CVPR 2026 Compute Transparency Champion
2026🏆한국지능시스템학회 학술대회 우수 논문상
2024🏆한국지능시스템학회 학술대회 우수 논문상
2024.02학위수여식 우등상 (Academic Honors, B.S. graduation)
2023.12🏆한국융합신호처리학회 추계학술대회 우수 발표 논문상
2023.11🏆한국지능시스템학회 추계학술대회 우수 논문상
2023.06🏆한국융합신호처리학회 하계학술대회 우수 발표 논문상
2023.04🏆한국지능시스템학회 춘계학술대회 우수 논문상
2022.06🏆한국융합신호처리학회 하계학술대회 우수 발표 논문상
2021.11KST 도로정비 AI 학습데이터 아이디어 공모전 우수상 · 스마트관광콘텐츠 콘테스트 동상
2021.08🏆한국인공지능융합기술학회 하계학술대회 우수 발표 논문상
2020.09연세대 미래캠퍼스 과학기술대학 학술대회 우수상

Let's talk research 🙌

Open to collaboration on generative-model safety and AI security.