Lists (4)
Stars
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
PORTGPT: Towards Automated Backporting Using Large Language Models(IEEE S&P2026)
[USENIX Security 25] PatchAgent is a LLM-based practical program repair agent that mimics human expertise.
BandFuzz is a collaborative fuzzing framework designed to optimize performance. BandFuzz uses reinforcement learning algorithms to schedule fuzzing instances in real-time.
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Prototype Implementation of "A Formal Approach to Multi-Layered Privileges for Enclaves" (NDSS 2025)
Formal Model of "A Formal Approach to Multi-Layered Privileges for Enclaves" (NDSS 2025)
QuickJS, the Next Generation: a mighty JavaScript engine
Blazingly 🔥 fast 🚀 memory vulnerabilities, written in 100% safe Rust. 🦀
A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.
A lightweight library for portable low-level GPU computation using WebGPU.
Python bindings for LLVM auto-generated from the LLVM-C API
AI wearables. Put it on, speak, transcribe, automatically
An LLVM-based instrumentation tool for universal taint tracking, dataflow analysis, and tracing.
The Social-Engineer Toolkit (SET) repository from TrustedSec - All new versions of SET will be deployed here.
CAMP: Compiler and Allocator-based Heap Memory Protection (USENIX Security 2024) ✨ Please give a star to https://github.com/cla7aye15I4nd/PatchAgent next door! 🌟😊
Community guide to securing and improving privacy on macOS.