Skip to content
View Kirito14IT's full-sized avatar
🌴
On vacation
🌴
On vacation
19 followers · 22 following

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report Kirito14IT

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
Kirito14IT/README.md

Hi, I'm Krico. Handshake, sparkles and a planet on an animated multicolor neon network. AI Safety, LLM Agents, Software Security.

Zhihua Wang
Senior Undergraduate in Computer Science and Technology
University of Shanghai for Science and Technology

🎓 Incoming M.Sc. Student, Fudan University (2027)
👨‍🏫 Advisor: Xingjun Ma
🧪 Lab: Fudan University logo Fudan FVL & TEAI logo TEAI

Academic Homepage Google Scholar Email

🤖 I build research prototypes around AI safety, LLM agents, software security analysis, and reliable multimodal systems.

🧠 Research Focus

  • 🛡️ AI safety and runtime governance for LLM agents.
  • 🤝 Multi-agent reinforcement learning for safety-constrained code generation.
  • 🔍 CodeQL-assisted software security analysis.
  • 👁️ Efficient neural models for visual correspondence pruning.

🚀 Selected Work

Project Research focus
🛡️ XSafeClaw Agent runtime safety and governance
🔍 VulnSeeker CodeQL and LLM-assisted vulnerability analysis
👁️ SFMambaNet Spectral-frequency state space models for correspondence pruning

Academic Homepage · Google Scholar · 📄 SFMambaNet Paper · Email

Pinned Loading

  1. wuyoscar/AISafetyHot-Hub wuyoscar/AISafetyHot-Hub Public

    Safety News & Research Monitor. https://aisafetyhot.com

    TeX 1.5k 18

  2. XSafeAI/XSafeClaw XSafeAI/XSafeClaw Public

    Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

    Python 166 7

  3. prompt-spider-ui prompt-spider-ui Public

    原生 JavaScript + Canvas 2D 的机械蜘蛛可视化 UI。普通演示零依赖；可选 MCP 接入自己的 Agent，实时展示任务，支持三套布局、主题定制、JSON 回放与独立项目导出。

    JavaScript 41 9

  4. VulnSeeker VulnSeeker Public

    English: > Automated security analysis pipeline that runs CodeQL queries and uses LLM to classify findings, filtering out false positives to surface true vulnerabilities. 中文： > 自动化安全分析工具，通过 CodeQL …

    Python 11 1