Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

ISC

Dataset for Paper, When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents

Open-source red teaming framework for MLLMs with 42+ attack methods

🙌 OpenHands: AI-Driven Development

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

🔥LeetCode solutions in any programming language | 多种编程语言实现 LeetCode、《剑指 Offer（第 2 版）》、《程序员面试金典（第 6 版）》题解

A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

A collection of MCP servers.

Model Context Protocol Servers

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️

Code for USENIX Security 2024 paper: Moderating Illicit Online Image Promotion for Unsafe User Generated Content Games Using Large Vision-Language Models.

Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning Models to enhance their security and reliability.

AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.

😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

[TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Latest Advances on System-2 Reasoning

Code for USENIX Security 2025 paper "JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation"

Synergistic fusion of privacy-enhancing technologies for enhanced privacy protection.

Deadline countdowns for academic conferences in Security and Privacy