Daoyuan Wu's repositories
daoyuan14.github.io
Daoyuan's homepage
acad-homepage.github.io
AcadHomepage: A Modern and Responsive Academic Personal Homepage
adversarial-explainable-ai
💡 Adversarial attacks on explanations and how to defend them
AgentKit
An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.
auto-code-rover
A project structure aware autonomous software engineer aiming for autonomous program improvement
AutoDroid
Source code for the paper "Empowering LLM to use Smartphone for Intelligent Task Automation"
bittensor
Internet-scale Neural Networks
DecodingTrust
A Comprehensive Assessment of Trustworthiness in GPT Models
DIE-engine
DIE engine
DrAttack
Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
governance-seatbelt
Make governance safer
ityfuzz
Blazing Fast Bytecode-Level Hybrid Fuzzer for Smart Contracts
LLift
The source code of project "LLift" (Enhancing static analysis with LLM)
lm-ssp
A reading list for large models safety, security, and privacy.
MiniCPM
MiniCPM-2B: An end-side LLM outperforms Llama2-13B.
oss-fuzz-gen
LLM powered fuzzing via OSS-Fuzz.
Pixel_GPU_Exploit
A kernel exploit for Pixel7/8 Pro with Android 14
POMABuster
POMABuster is an automated engine to detect Price Oracle Manipualtion Attack (POMA) to blockchain oracles.
PurpleLlama
Set of tools to assess and improve LLM security.
PyRIT
The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.
qdrant
Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
rebuff
LLM Prompt Injection Detector
retrowrite
RetroWrite -- Retrofitting compiler passes through binary rewriting
safe-rlhf
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Scrapegraph-ai
Python scraper based on AI
www-project-top-10-for-large-language-model-applications
OWASP Foundation Web Respository