Ph.D. Candidate in Cybersecurity
Korea University · Seoul & Abu Dhabi
Designing domain-specific generative models (DiT, GAN) to address data insufficiency issues in cybersecurity, while investigating vulnerabilities in LLMs & agentic AI.
I am an AI & Security Researcher based in both the UAE and South Korea. My approach to security research is built on five years of experience at the Agency for Defense Development (ADD), as well as international joint projects with the UAE Ministry of Defense.
As a Ph.D. candidate in Cybersecurity at Korea University, I have mainly explored how generative models can improve cybersecurity, designing diffusion transformers (DiT) and GANs to address data insufficiency in physical and wireless security, including RF signal processing and side-channel analysis.
For my next steps, I plan to investigate the flip side: uncovering the inherent vulnerabilities within LLMs and agentic AI systems, applying my structural understanding of generative models to ensure their trustworthiness.
My research lies at the intersection of AI and cybersecurity.
Designing security-specific generative models (diffusion transformers, GANs) to address data insufficiency in physical and wireless security, including RF signal processing and side-channel analysis (SCA).
Advancing CTI using NLP and LLMs to analyze attack campaigns: TTP extraction, attribution, and generating campaign variants for group identification.
Transitioning toward securing AI itself, applying structural understanding of generative models to investigate vulnerabilities within LLMs and agentic AI systems, and to ensure their trustworthiness.
Korea University, Seoul, Republic of Korea
Domain-Specific Generative Models for Data Augmentation in Multi-Layer Cybersecurity
Advisors: Prof. Sangjin Lee & Prof. Seokhie Hong | Expected: Aug 2026
Korea University, Seoul, Republic of Korea
Full Tuition Scholarship, Ministry of National Defense | Advisor: Prof. Jongin Lim
Korea University, Seoul, Republic of Korea
Taught graduate-level course in Computer Networks.
Indiana University Bloomington, IN, USA (Remote)
Explored adversarial attacks on ML systems in autonomous vehicles (Advisor: Prof. Hyungsub Kim).
Ministry of National Defense, Republic of Korea / UAE
Agency for Defense Development (ADD), Seoul, Republic of Korea
Exploiting Per-Core Leakage: Electromagnetic Side-Channel Monitoring of Multicore Architectures
ACM/IEEE Design Automation Conference (DAC), Jul. 2026
BK21+ IF: 3 · Top-tier EDA/Hardware Conference
LeakDiT: Diffusion Transformers for Trace-Augmented Side-Channel Analysis
IEEE Computer Architecture Letters, Vol. 25, No. 1, pp. 5–8, Jan./Jun. 2026
Multi-Step LLM Pipeline for Enhancing TTP Extraction in Cyber Threat Intelligence
IEEE Access, Vol. 13, pp. 179696–179710, Oct. 2025
Enhancing Modulation Classification via Diffusion Transformers for Drone Video Signal Processing
IEEE Signal Processing Letters, Vol. 32, pp. 3325–3329, Aug. 2025
UniQGAN: Towards Improved Modulation Classification With Adversarial Robustness Using Scalable Generator Design
IEEE Transactions on Dependable and Secure Computing (TDSC), Vol. 21, No. 2, pp. 732–745, Mar./Apr. 2024
JCR 2023 Top 4.9% in CS, Software Engineering · Top-tier Security Journal
Camp2Vec: Embedding Cyber Campaign With ATT&CK Framework for Attack Group Analysis
ICT Express, Vol. 9, No. 6, pp. 1065–1070, Dec. 2023
Exploiting TTP Co-occurrence via GloVe-Based Embedding With ATT&CK Framework
IEEE Access, Vol. 11, pp. 100823–100831, Sep. 2023
BAN: Predicting APT Attack Based on Bayesian Network With MITRE ATT&CK Framework
IEEE Access, Vol. 11, pp. 91949–94968, Aug. 2023
Anomaly Dataset Augmentation Using Sequence Generative Models
IEEE International Conference on Machine Learning and Applications (ICMLA), Dec. 2019
Opcode Sequence Amplifier Using Sequence Generative Adversarial Networks
International Conference on ICT Convergence (ICTC), Oct. 2019
Multi-Domain Side-Channel Analysis for Anomaly Detection in Embedded System
Submitted to IEEE Embedded Systems Letters
(Blind Review)
Submitted to ACM CCS 2026
Method for Augmenting Cyber Attack Campaign Data to Identify Attack Group, and Security
Korea Patent Application No. 10-2024-0176082, Dec. 2024
Information Identification Method and Electronic Apparatus Thereof
Korea Patent Application No. 10-2024-0006106, Jan. 2024
Method for Training Attack Prediction Model and Device Therefor
U.S. Patent No. US20230308462A1, Sep. 2023
Apparatus, Method, Computer-readable Storage Medium and Computer Program for Generating Operation Code
Korea Patent No. 10-2246797, Apr. 2021
EM-Based Anomaly Detection using a Dual-Domain Approach
KIISC Winter Conference (CISC-W'25), Nov. 2025
Outstanding Paper Award
A Statistical Time-Domain Approach to Anomaly Detection for Robotic-Arm MCU
KIMST Fall Conference, Nov. 2025
Reinforcement Learning for Parameter Optimization in CADO-NFS Polynomial Selection
KIISC Winter Conference (CISC-W'25), Nov. 2025
Enhanced DDoS Detection via Traffic Volume-Based Labeling and Transfer Learning
Journal of Internet Computing and Services (JICS), Vol. 26, No. 4, pp. 1–8, Aug. 2025
User Behavior Embedding via TF-IDF-BVC for Web Shell Detection
Journal of The Korea Institute of Information Security & Cryptology (JKIISC), Vol. 34, No. 6, pp. 1231–1238, Dec. 2024
Korea University, Seoul, Republic of Korea
View CertificateCISC-W'25, KIISC
UAE Ministry of Defense (UAE-ROK Engagement Program)
View CertificateMinistry of National Defense, Republic of Korea
I am open to academic collaborations, postdoctoral opportunities, and research discussions in AI security and cybersecurity. Feel free to reach out!
Download Full CV