Researcher, agent builder, and security-minded thinker.
This page provides the professional context behind the portfolio: the doctoral research agenda, the investigation-informed perspective, and the way I approach AI agents and systems intended for serious real-world use.
- Current Role
- Doctoral Researcher
- Institution
- National Yang Ming Chiao Tung University
- Primary Lens
- AI agents, trustworthy AI, and deployment realism
Current Areas of Work
Trustworthy AI agents and systems for operational deployment
IDE-like AI agent systems for research, coding, and analyst workflows
ASR + LLM + RAG pipelines for speech intelligence and evidence-aware analysis
Security, privacy, and evaluation for agentic systems used in high-stakes settings
Human review, traceability, and decision support in analyst-facing workflows
Professional Path
Current
Doctoral Researcher, NYCU Artificial Intelligence in Medical Imaging / Signal Analysis Lab
Researching trustworthy AI systems, AI agents, medical cybersecurity, speech intelligence, grounded LLM workflows, and security-aware evaluation for real-world deployment.
Previous
Cybercrime Investigation
Worked on digital evidence, online fraud analysis, OSINT, and operational reasoning in high-stakes investigative settings.
Cross-Disciplinary
Investigation-Informed Systems Thinking
Bringing evidence awareness, adversarial thinking, and operational discipline into the way AI agents and systems are designed and evaluated.
Ongoing
Research and Technical Communication
Developing research case studies, technical writing, and speaking material around trustworthy AI, agent systems, speech systems, and deployment risk.
Professional Narrative
I am a doctoral researcher in the Artificial Intelligence in Medical Imaging / Signal Analysis Lab at National Yang Ming Chiao Tung University (NYCU), where my work sits at the intersection of AI agents, trustworthy AI, speech and language pipelines, and security-aware evaluation.
Before doctoral research, I worked in cybercrime investigation. That experience still shapes how I think about evidence, adversarial behavior, failure analysis, and the difference between a model that performs well in isolation and a system that can be trusted in practice.
Today, I focus on AI agents, IDE-like agent systems, ASR + LLM + RAG workflows, speech intelligence, deployable AI systems, and governance-minded thinking for regulated or security-sensitive environments. Recent speaking and paper activity includes an official CYBERSEC 2026 breakout session on cybersecurity design for AI software medical devices, as well as two English CISC 2025 conference papers on AI-era ransomware evolution and threat pulse modeling for ZTAID-aligned zero-trust maturity assessment.
Current speaking and paper activity
CYBERSEC 2026
AI 軟體醫材的資安實戰：從美國 FDA 524B 規範到 Threat Modeling 與 Patch SLA 的完整落地
CISC 2025
Evolution and Defense Challenges of Ransomware-as-a-Service in the AI Era: A Technical and Strategic Analysis Using Medusa and CrazyHunter as a Case Study
English conference paper examining how AI-era RaaS operations evolve through BYOVD, LOTL, covert C2, and adaptive tradecraft, then mapping those threats to a ZTAID-grounded zero-trust defense strategy.
CISC 2025
Integration of Threat Pulse Modeling into the ZTAID Zero Trust Maturity Assessment Model: An Analytical Framework
English conference paper proposing Threat Pulse Modeling (TPM) as a way to translate live cyber threat intelligence into ZTAID maturity signals for continuous zero-trust assessment.
Selected Signals
- Interdisciplinary profile spanning research, agent and system building, and security-minded reasoning.
- Current work connects AI agents, ASR, LLM/RAG pipelines, evaluation design, and deployment constraints.
- Open to collaboration with research groups, technical teams, and high-stakes AI stakeholders.
Methods / Technical Toolkit
AI / Agent Systems
Speech / Language
Security / Operations
Research / Evaluation
Work together
I welcome thoughtful conversations around AI agents, IDE-like agent systems, trustworthy AI, speech and language systems, and deployment in security-sensitive or regulated environments.