safety - 技术专题

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

👷 TypeScript's largest type utility library

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

🔐CNCF Security Technical Advisory Group -- secure access, policy control, privacy, auditing, explainability and more!

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

List of resources about programming practices for writing safety-critical software.

The Domain-Correct Quantities and Units Library for C++ — full quantity kind safety, ISO 80000 compliant, C++29 standardization candidate.

保护你的浏览器指纹 | Protect Your Browser Fingerprints | Chrome, Edge, Firefox | 扩展 / Extension

☕ Latte: the safest & truly intuitive templates for PHP. Engine for those who want the most secure PHP sites.

Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

Open-source vulnerability disclosure and bug bounty program database

[EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)

A robust option type for C#

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

The repository is for safe reinforcement learning baselines.

Web 端反爬技术方案