Skip to content
View Xxxxsir's full-sized avatar
:octocat:
Life is too short for boring things.
:octocat:
Life is too short for boring things.

Highlights

  • Pro

Block or report Xxxxsir

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
Xxxxsir/README.md

I'm Justin, a prospective graduate student for 26 fall
and currently a researcher assistant in trustworthy ML.

Homepage Google Scholar

Profile Details

🌱 I’m currently exploring topics in AI security, Agent safety, and bias & fairness of LLMs.

🛡️ Previously, I had a broad interest in Web Security and Capture The Flag (CTF) competitions.

🤔 I’m open to research collaborations and remote research opportunities related to trustworthy AI.


🌈 Tech Stack:

gitmarkdownlinuxdockercbashpythonjavajavascriptpytorchpandassqliteMySQL redistailwindcssdaisyuisasstypescript vuenginx


🏆 My Github Stats:

GitHub Stats Top Langs

GitHub Trophies


📈 Badge:

Visitor Count Followers Stars Last Commit Repo Size

Pinned Loading

  1. SleepEvasion SleepEvasion Public

    A tool used the Sleep Obfuscation and Memory encrypt technique to evade the anti-virus.A Proof of Concept,only used for study purpose.一种使用睡眠混淆和内存加密技术来逃避杀毒软件检测的工具。POC,仅用于研究目的。

    C++ 6 1

  2. AntiAV-evading-antivrius AntiAV-evading-antivrius Public

    Using Hooking techniques and memory separation techniques to achieve evasion of shellcode detection, tested to bypass antivirus software such as ESET, 360, Huorong, and others.

    C++ 5 2

  3. Score-Judge-Bias Score-Judge-Bias Public

    Score-Judge is a comprehensive evaluation framework designed to detect and mitigate preference bias in large language model (LLM) outputs. It provides a complete end-to-end pipeline — from data pre…

    Python 1

  4. Lethe Lethe Public

    the code implementation of the paper "Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution"

    Python 1