NVIDIA garak 教程：构建完整防御性 LLM 红队工作流
NVIDIA garak Tutorial: Build a Complete Defensive LLM Red-Teaming Workflow with Custom Probes and Detectors
对于需要系统化测试 LLM 安全性的团队，这个教程提供了从零到自定义探针的完整路径，建议直接跟着步骤搭建自己的红队流程。
本文是一篇关于 NVIDIA garak 框架的详细教程，指导用户如何构建防御性的大语言模型红队测试工作流。教程涵盖了环境搭建、插件发现、干运行、在 Hugging Face 生成器上进行真实模型扫描以及多探针评估。
用户可以通过分析安全分数和攻击成功率来检查标记输出，并扩展 garak 以添加自定义探针和检测器。最后，教程演示了如何以 AVID 格式导出结果，实现结构化漏洞管理。
NVIDIA garak Tutorial: Build a Complete Defensive LLM Red-Teaming Workflow with Custom Probes and Detectors
This tutorial walks through NVIDIA garak as an end-to-end framework for defensive LLM red-teaming. It covers setup, plugin discovery, dry runs, real-model scans on a Hugging Face generator, and multi-probe evaluations. The workflow then analyzes safety scores and attack success rates, inspects flagged outputs, and extends garak with a custom probe and detector. It closes by exporting results in AVID format for structured vulnerability The post NVIDIA garak Tutorial: Build a Complete Defensive LLM Red-Teaming Workflow with Custom Probes and Detectors appeared first on MarkTechPost .
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Key entities and technical topics under continuous tracking include NVIDIA garak, LLM 安全, 红队测试, 自定义探针.
Primary source verification: published directly by marktechpost with first-party authority. Cross-source corroboration: 10 independent sources have covered this development (including Thomas Wolf, Paul Couvert, Together AI), confirming industry-wide signal strength.
