Canonical URL: [https://www.taislab.co.kr/cv/](https://www.taislab.co.kr/cv/) # CV Academic profile, employment, research, supervision, service, and impact ### General Information **Full Name** — Younghan Lee **Current Position** — Assistant Professor (tenure-track), Sungshin Women's University **Email** — 201younghanlee@gmail.com **Website** — www.taislab.co.kr **ORCID** — 0000-0001-8414-966X ### Academic Profile - AI-security researcher working on automated vulnerability repair, vulnerability detection, secure code generation, federated-learning security, and the assurance of LLM-based and agentic systems. ### Education - Mar 2017 – Feb 2024 ** Seoul, Republic of Korea ###### PhD in Electrical and Computer Engineering ** — Seoul National University - Thesis: Solving Contemporary Security Problems in Deep Learning - Advisor: Professor Yunheung Paek - Sep 2013 – Jun 2016 ** London, United Kingdom ###### BEng in Electrical and Electronic Engineering ** — Imperial College London - Degree awarded Aug 2016 ### Academic Employment - Sep 2024 – Present ** Seoul, Republic of Korea ###### Assistant Professor (tenure-track) ** — Sungshin Women's University ** — Department of Convergence Security Engineering - Mar – Aug 2024 ** Seoul, Republic of Korea ###### Postdoctoral Researcher ** — Seoul National University ** — Department of Electrical and Computer Engineering - Supervisor: Professor Yunheung Paek - Mar – Aug 2024 ** Seoul, Republic of Korea ###### Lecturer ** — Soongsil University ** — Department of AI Techno-Convergence - Mar – Aug 2024 ** Seoul, Republic of Korea ###### Lecturer ** — Sungshin Women's University ** — Department of Convergence Security Engineering ### Research Areas - LLM4SEC (LLMs for Security): automated vulnerability repair, vulnerability detection, secure code generation, and kernel code fault localization. - SEC4LLM & AI/ML Security: RAG security, IaC agent assurance, ROS 2 agent assurance, and federated learning security. ### Selected International Publications - 2026 ###### VulScope: Software Vulnerability Detection via Local Context Analysis and Verification - Hyunjun Kim, Younghan Lee, Woorim Han, Subin Yun, Kang-Won Lee, and Yunheung Paek. - Empirical Software Engineering. Accepted for publication on 11 May 2026; final bibliographic details pending. - Role: Co-first author. [Publication](/publications/#kim2026vulscope) - 2026 ###### Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair - Woorim Han, Yeongjun Kwak, Miseon Yu, Kyeongmin Kim, Younghan Lee, Hyungon Moon, and Yunheung Paek. - 48th IEEE/ACM International Conference on Software Engineering (ICSE). DOI 10.1145/3744916.3773167. - Role: Co-corresponding author. [Publication](/publications/#han2026rethinking) - 2026 ###### PI-FD: Property Inference Attacks on Federated Learning With Distillation via Synthetic Data Generation - Yungi Cho, Miseon Yu, Jaejin Kim, Younghan Lee, and Yunheung Paek. - IEEE Access 14, 101398–101414. DOI 10.1109/ACCESS.2026.3700259. - Role: Co-corresponding author. [Publication](/publications/#cho2026pifd) - 2025 ###### Poster: A Case Study on Automated Vulnerability Repair Using Pre-Trained Language Models - Woorim Han, Miseon Yu, Younghan Lee, Hyungon Moon, and Yunheung Paek. - IEEE Silicon Valley Cybersecurity Conference, 1–3. DOI 10.1109/SVCC65277.2025.11133621. - Role: Co-corresponding author. [Publication](/publications/#han2025poster) - 2024 ###### VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification - Yungi Cho, Woorim Han, Miseon Yu, Younghan Lee, Ho Bae, and Yunheung Paek. - ESORICS, LNCS 14985, 291–312. DOI 10.1007/978-3-031-70903-6_15. - Role: Co-author. [Publication](/publications/#cho2024vflip) - 2023 ###### FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models - Younghan Lee, Yungi Cho, Woorim Han, Ho Bae, and Yunheung Paek. - ESORICS, LNCS 14347, 65–84. DOI 10.1007/978-3-031-51482-1_4. - Role: First author. [Publication](/publications/#lee2023flguard) - 2022 ###### Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices - Younghan Lee, Sohee Jun, Yungi Cho, Woorim Han, Hyungon Moon, and Yunheung Paek. - ESORICS, LNCS 13556, 364–383. DOI 10.1007/978-3-031-17143-7_18. - Role: First author. [Publication](/publications/#lee2022precise) - 2021 ###### Learn2Evade: Learning-Based Generative Model for Evading PDF Malware Classifiers - Ho Bae, Younghan Lee, Yohan Kim, Uiwon Hwang, Sungroh Yoon, and Yunheung Paek. - IEEE Transactions on Artificial Intelligence 2(4), 299–313. DOI 10.1109/TAI.2021.3103139. - Role: Co-first author. [Publication](/publications/#bae2021learn2evade) ### Selected Funded Research Projects - Jul 2024 – Dec 2026 ###### AI-Based Automated Vulnerability Detection and Secure Code Generation ** — IITP Cybersecurity International Collaborative R&D Programme - Participating Researcher, project RS-2024-00439819 - May 2024 – Dec 2028 ###### Quantitative Sleep Microstructure Optimisation for Cognitive and Emotional Enhancement ** — National Research Foundation of Korea - Participating Researcher, project RS-2024-00359247 - Apr 2024 – Mar 2027 ###### Confidential-Computing-Based Privacy-Preserving Federated Learning Platform and Security Technologies ** — National Research Foundation of Korea - Participating Researcher, project RS-2024-00351898 ### Student Supervision and Examination - Advised three student papers published in the ASK 2026 proceedings on narrative injection, execution-centred ROS 2 code generation, and RAG security. - Supervised a 2025 undergraduate research project on LLM-based obstructive-sleep-apnoea severity classification that led to a conference poster and journal article. - Master's thesis examiner for work on SBOM-based risk assessment in software-supply-chain security, 2025. ### Academic and Professional Service - 2024–Present ###### Leadership and Conference Service ** — Korea Information Processing Society - Editorial Board Member, KIPS Review, 2025–present - Executive Secretary, Artificial Intelligence System Research Group, 2024–present - Member, Executive Director Board, 2024–2025 - Vice Chair, Academic Committee, ASK 2025 - Programme Committee Member, WISA 2026 - Programme Organising Committee Member, 2026 Joint Workshop of the AI Systems and Data Security & Privacy Research Groups - Session Chair, ASK 2025, ACK 2025, and ASK 2026 - 2026 ###### External and Alumni Service - Secretariat Member, Imperial College London Alumni Association Korea - External Evaluator, Seocho Resident Living Lab Idea Competition - 2025–2026 ###### Peer Review - IEEE Transactions on Dependable and Secure Computing, 2025 - ACM Transactions on Software Engineering and Methodology, 2025 - Journal of Information Processing Systems, 2025–2026 - KIPS Transactions on Computer and Communication Systems, 2025–2026 ### Selected Intellectual Property and Impact - 3 Dec 2025 / 17 Jun 2026 ###### Korean Patent Applications 10-2025-0189598 and 10-2026-0110736 - Backdoor-robust multimodal-model training and inference - Co-inventors: Ho Bae, Youngseo Kim, and Younghan Lee - Feb 2026 ###### External Advisory Engagement ** — Software Policy Research Institute - Consultation on the impact of AI development on the software industry - 28 Jan 2026 ###### Korean Patent Application 10-2026-0016350 - Multi-LLM clinical decision support for automated interpretation of sleep questionnaires and sleep-disorder correlation search - Co-inventors: Jooyoung Kim and Younghan Lee - 10 Dec 2025 ###### Computer Program Copyright Registration C-2025-056782 - Multimodal Learning Model and Method for Backdoor Defence Using Randomised Response - Joint institutional registration by the university-industry cooperation foundations of Ewha Womans University and Sungshin Women's University - Younghan Lee is named in the institutional inventor disclosure - 27 Dec 2024 ###### Computer Program Copyright Registration C-2024-056087 - Positional and REM-Dominant OSA Classification Model with Differential Privacy - Joint institutional registration by the university-industry cooperation foundations of Ewha Womans University and Sungshin Women's University - Younghan Lee is named as the representative inventor in Sungshin Women's University's institutional disclosure ### Selected Invited Teaching and Talks - 28 Apr 2026 ###### LLM Security: RAG Poisoning Attacks and Defences ** — Modulabs Everyone's Lab - Jan 2026 ###### AI Security: Leveraging Large Language Models to Address Security Challenges ** — Korea–Central Asia STEM Youth Silk Road programme - Three-hour English-medium international lecture - 2025 ###### LLM-Based Automated Vulnerability Detection and Patch Generation ** — Ulsan National Institute of Science and Technology - 2025 ###### AI Agents and Automation: Current Research Trends and Innovative Applications ** — Korea Information Processing Society AI Systems Research Group - 2024 ###### Multi-Agent Systems ** — Korea Information Processing Society AI Systems Research Group Workshop - 17 Apr 2024 ###### Security of Deep Learning Models in IoT/Edge Devices ** — Seoul National University of Science and Technology - Aug 2023 ###### Invited Seminar ** — Information Security Specialized University Support Programme, Chonnam National University - 2022 ###### Theory of Information Security ** — Ewha Womans University