Skip to content
View lzwhehe's full-sized avatar
🎯
Focusing
🎯
Focusing
  • JAIST

Block or report lzwhehe

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. 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
lzwhehe/README.md
Liu Zhuowen — AI Security Engineer · LLM & Agent Security

中文 English 日本語

Email ▶ 全部在线 Demo

研究主线 · 先评测、再防御:先用红队评测量出提示注入检测器与告警研判 Agent 在真实 Agent 场景里的失效,再把结论做成证据可核验、可私有化部署的告警研判 Agent。

Highlights

🛠️ 工程项目 · 均开源、可在线运行

Probewise

▶ 在线 Demo 源码

lunxun-xiaomi

▶ 在线 Demo 源码

repo-vuln-scanner

▶ 在线 Demo 源码

security-radar

▶ 在线 Demo 源码

LeakLens

▶ 在线 Demo 源码

Demo 部署在国内服务器;轮询小秘与 LeakLens 的 Demo 使用合成数据,扫描类工具仅用于授权安全测试。

🔬 科研 · 先评测、再防御

bench

预印本 arXiv 代码

hesp

预印本 arXiv 代码

forged

预印本

kushulan

代码

🧰 技能

Skills

📮 联系:ryutakubunwork@gmail.com

Popular repositories Loading

  1. HESP HESP Public

    让 7B 模型胜任告警分诊 | Making 7B models capable of alert triage

    TeX 2

  2. kushulan-papercut-blora kushulan-papercut-blora Public

    Ku Shulan papercut research archive: datasets, SDXL B-LoRA checkpoints, generated results, and verified migration tools.

    Python 1

  3. repo-vuln-scanner repo-vuln-scanner Public

    静态漏洞扫描器:凭证泄露/CVE/CWE 规则匹配与可视化

    JavaScript 1 1

  4. probewise probewise Public

    Evidence-backed security alert triage on LangGraph — picks the next check by information gain, every verdict ships with a verifiable proof. MCP server + Agent Skill, OpenTelemetry, human-in-the-loop.

    Python 1

  5. Js-DataStruct Js-DataStruct Public template

    JavaScript

  6. i483-source_code_LIU i483-source_code_LIU Public

    i483's source code

    Python