Skip to main content
redteams.ai
All tags

# LLM-attacker

1 articletagged with “LLM-attacker

PAIR Automated Jailbreak

Using a second LLM as an automated attacker to iteratively generate and refine jailbreak prompts against a target model, implementing the Prompt Automatic Iterative Refinement technique.

jailbreakingPAIRautomated-red-teamingLLM-attackeriterative-refinementred-teaming
Advanced