Machine Learning and Artificial Intelligence Lab (MLAI)
Seoul, Korea
under the supervision of Professor Sung Ju Hwang Sung Ju Hwang
POSTECH 2016.3 ~ 2021.8
Pohang, Korea
B.S. - Computer Science
Achieved GPA 3.70, Major GPA 3.96 (4.3 scale) Magna Cum Laude
Experience
Theori 2023.11 ~ Current
Seoul, Korea
AI for Offensive Security
AI Engineer
Autonomous AI Agent framework for finding Security Vulnerabilities in Blackbox Web Applications
Whitebox Threat Scenario modeling and fuzzing with LLM Agents (AIxCC)
AI security consultant report generation with Retrieval-Augemented Generation(RAG) LLM models
Trained custom fine-tuned models for various security tasks (Webpage Classification, PII Extraction, CWE Classification, ...)
Lead of Xint Autopen: Offensive Security AI Engine in Xint
Automated Pentesting with AI: IDOR, XSS, Open Redirect, Sensitive Page Detection by crawling and fuzzing blackbox web applications
Intelligent Vulnerability Detection: Identify complex security flaws, such as IDOR and XSS, by analyzing application logic and user behavior patterns.
Autonomous Page and Component Analysis: Automatically discover and test web pages and components for a wide range of security issues, including unauthorized access to admin pages and privileged APIs.
CTF Player
Engaged in various CTF (Capture-The-Flag) competitions, including DEFCON, as a member of teams "The Duck" and "Maple Mallard Magistrates".
Smart Factory Solution Development for Quality Assurance in POSCO products
Training and Deployment of Image Classfication and Segmentation Models
Deep Learning Production on Nvidia Jetson Xavier, Jetson Nano
Deployment of Tensorflow C api, C++ api, TF Lite, PyTorch in Windows OS
Web App Developer
Integrated Deep Learning Web Application for Image Annotation + Training/Inference
Tensorflow & Keras, Redis, Flask, Apache, HTML Canvas
Naver 2017 Summer
Gyeonggi, Korea
Smart Store Platform Dept. (Internship)
Big Data Server Management
Big Data extraction & graph representation using Spark SQL & Apache Zeppelin
Open Source Commit : expanded data download limit on Apache Zeppelin
Hadoop, Hbase configuration and optimization regarding network topology
Server programming using Java Spring & Scala
Publications
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models arXiv
We propose HarmAug, a data augmentation method that distills a large safety guard model into a smaller 435M-parameter model by generating harmful instruction-response pairs using LLMs, resulting in a model that matches or outperforms larger models in F1 score and AUPRC while significantly reducing computational costs.
Large Language Models, AI Safety, Jailbreak, AI Red-Teaming, LLM Guard Models
Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems arXiv
We show that Large language models (LLMs) often incorporate intentional biases akin to Political Correctness (PC) during safety alignment, which can result in discrepancies in their responses based on sensitive attributes, raising concerns about fairness and the effectiveness of these safety measures.
Large Language Models, AI Safety, Jailbreak, Politics, Social Biases
Sequential Decision Making with only Return and Action Master's Thesis, KAIST
Relaxation of Markov Decision Processes (MDP) that requires fewer conditions for easier application in real-world
Wide interest in almost every CS related topic : AI, ML, Web, Security, System, Network, Graphics, ...
Always trying to learn from the internet : papers, projects, blogs, documents from everywhere
Currently most interested in AI for Security, AI for Offensive Security, AI for Cybersecurity
Certifications
IELTS Academic (International English Language Testing System) 2023.07.01
Scored 7.5 : Good User
"The test taker has operational command of the language, though with occasional inaccuracies, inappropriate usage and misunderstandings in some situations. They generally handle complex language well and understand detailed reasoning."
New TEPS (Test of English Proficiency developed by Seoul National University) 2020.09.19
Scored 519, percentile rank of 96.67%
"Near-native level of English proficiency. A score at this level typically indicates the highest English proficiency for a non-native speaker. A test taker at this level is able to perform technical tasks required in a specialized field after short-term training."
Extracurricular Activities
Postech Laboratory for Unix Security (PLUS) Certified Member, 2017 ~
PLUS is an undergraduate cyber-security study club at Pohang University of Science and Technology (POSTECH).
PLUS has competed in several domestic and international cyber-security(CTF) competitions since 1992.
PDAO is a blockchain community and open-source foundation based at POSTECH, designed as a Decentralized Autonomous Organization (DAO) to promote blockchain development, research, and education.
PDAO operates through the PDAO Chain, a multi-chain governance platform, and focuses on community building, open-source projects, and integrating cryptocurrency into university operations.
Honors and Awards
Hacking & Security
DEFCON CTF | #1 on Quals, #1 on Finals [Maple Mallard Magistrates] 2024