×ばつ Computer Vision ×ばつ VLMs · Evidence-grounded, reliable intelligent systems - niansia"> ×ばつ Computer Vision ×ばつ VLMs · Evidence-grounded, reliable intelligent systems - niansia" /> ×ばつ Computer Vision ×ばつ VLMs · Evidence-grounded, reliable intelligent systems - niansia" />×ばつ Computer Vision ×ばつ VLMs · Evidence-grounded, reliable intelligent systems - niansia" />
Skip to content

Navigation Menu

Sign in
Sign up
@niansia
niansia
Follow
M.S. student @ NYCU (one-year leave) · AI Security ×ばつ Computer Vision ×ばつ VLMs · Evidence-grounded, reliable intelligent systems

Highlights

  • Pro

Block or report niansia

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
niansia /README.md

Hi, I'm Niansia 👋

繁體中文 · 简体中文 · English

M.S. student · National Yang Ming Chiao Tung University

AI Security ×ばつ Trustworthy Evaluation ×ばつ Evidence-Grounded Systems

Researching the security, robustness, and reasoning capabilities of visual and multimodal intelligent systems.

Currently taking a one-year leave of absence from the master's program.

Website · Research · Portfolio · Email

About

I earned my degree in Computer Science from Yuan Ze University (YZU) and am now enrolled in a master's program at National Yang Ming Chiao Tung University (NYCU). I am currently taking a one-year leave of absence. My primary interests lie at the intersection of AI security, computer vision, and vision-language models, with an emphasis on reliable multimodal reasoning and evaluation.

I turn research questions into reproducible experiments and working systems. Current projects include KCrashLab, a deterministic platform for reproducible Windows driver reliability research, and ContextSec, a product-security decision layer for AI coding agents.

Research interests

🛡️ AI & Multimodal Security

  • Security and robustness of multimodal AI
  • Adversarial and failure-mode analysis
  • Content integrity and verification
  • Trustworthy, auditable evaluation

👁️ Vision & Multimodal Intelligence

  • Computer vision and vision-language models
  • Multimodal reasoning and memory
  • Evaluation under real-world uncertainty
  • Reproducible failure analysis

Selected projects

ContextSec deterministic product-security decision flow
ContextSec
A research-preview, deterministic product-security decision layer for AI coding agents. It derives applicable risk packs from bounded repository evidence, composes cross-context controls, and emits a verifiable Control Evaluation Ledger with an explicit release gate. Merriv release evidence architecture
Merriv
A pre-alpha, vendor-neutral release-evidence layer for deployable AI models. It binds exact artifacts, paired evaluation, statistical policy, provenance, and regression onset into a portable Model Change Report for independent verification before promotion.
KCrashLab deterministic crash research evidence workflow
KCrashLab
Evidence-frozen research platform for deterministic Windows driver reliability experiments. It combines canonical cases, resumable campaigns, exact failure signatures, minimization, 3/3 simulated replay, and semantic artifact verification while clearly separating simulated evidence from the gated Windows-lab track. ChromaRecover evidence-first computer vision architecture
ChromaRecover
An experimental public-alpha, local-first Python toolkit for recovering spatial structure carried by subtle color differences. It tests competing chromatic hypotheses, preserves auditable artifacts, and abstains when evidence is weak.

Tools

Python · PyTorch · OpenCV · scikit-learn · Jupyter · C# / .NET · React · TypeScript · Node.js · SQLite · Git

Contact

I welcome thoughtful conversations about AI security, CV / VLM reasoning, trustworthy machine learning, reproducibility, and research tooling. Feel free to contact me at wilbur930202@gmail.com .

Pinned Loading

  1. ContextSec ContextSec Public

    Deterministic product-security decision layer for AI coding agents.

    Python

  2. Merriv Merriv Public

    Vendor-neutral release evidence for deployable AI models.

    Python 1

  3. ai-repo-gardener ai-repo-gardener Public

    Evidence-backed garbage collection, architecture guidance, and Python house-style drift analysis for AI-edited repositories.

    Python 1

  4. ChromaRecover ChromaRecover Public

    Evidence-first recovery of spatial structure carried by subtle color differences

    Python 1

  5. KCrashLab KCrashLab Public

    Evidence-first deterministic simulation and reproducibility tooling for Windows kernel-crash research.

    C#

  6. PSG PSG Public

    Persistent task boundaries, project decisions, and evidence-based ship gates for AI coding agents.

    Python 1

AltStyle によって変換されたページ (->オリジナル) /