LLM Training Data Extraction

Extract sensitive training data (PII, API keys, intellectual property, or code) directly from a deployed Large Language Model (LLM). This AI Red Teaming skill focuses on forcing models to regurgitate memorized, unredacted data from their massive internet-scraped datasets through repetition attacks, prefix continuation, and context window manipulation.

ShulkwiSEC Updated 27 repo stars
Demo

File contents

ShulkwiSEC/bb-huge commit c88dd2574e

Frequently asked questions

npx get-skill add shulkwisec/llm-training-data-extraction