# Red-Teaming Lab: GCG + PAIR + AutoDAN + Prompt Injection Robustness

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-red-teaming-gcg-pair-autodan
> Updated: 2026-05-14T14:43:03.889Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part XVIII — Compliance, Governance & Red-Teaming
**TLDR:** Mandatory before production deploy: red-team probe. GCG (Greedy Coordinate Gradient — adversarial suffix attack), PAIR (Prompt Automatic Iterative Refinement — LLM attacks LLM), AutoDAN (jailbreak auto-generation), prompt injection (malicious instruction in RAG context). Cookbook's open red-team corpus + scoring method.