Lists (7)
Starred repositories
PatchEval: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
Macaron is an extensible supply-chain security analysis framework from Oracle Labs that supports a wide range of build systems and CI/CD services. It can be used to prevent supply chain attacks, de…
LLVM (Low Level Virtual Machine) Guide. Learn all about the compiler infrastructure, which is designed for compile-time, link-time, run-time, and "idle-time" optimization of programs. Originally im…
ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents
Propagation-Based Vulnerability Impact Assessment for Software Supply Chains | ASE 2025 🔬
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Responsive, simple, clean and content-focused Hugo theme based on the MH Magazine lite WordPress theme
Code for San2Patch("Logs In, Patches Out: Automated Vulnerability Repair via Tree-of-Thought LLM Analysis")
The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents
Learning Deep Representations of Data Distributions
A lightweight, powerful framework for multi-agent workflows
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
BandFuzz is a collaborative fuzzing framework designed to optimize performance. BandFuzz uses reinforcement learning algorithms to schedule fuzzing instances in real-time.
Buttercup finds and patches software vulnerabilities
Securing open-source package ecosystems by originating, validating, and augmenting build attestations.
Supply-chain Levels for Software Artifacts
《解构大语言模型：从线性回归到通用人工智能》配套代码
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
🤗 smolagents: a barebones library for agents that think in code.