PyRIT icon indicating copy to clipboard operation
PyRIT copied to clipboard

FEAT: Add nesting and prepend/append jailbreaks from papers

Open jl8771 opened this issue 1 year ago • 2 comments

Description

Add jailbreak prompt templates from following papers:

  1. A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
    • Code nesting
    • Table nesting
    • Text continuation nesting
  2. Jailbroken: How Does LLM Safety Training Fail?
    • Prefix injection
    • Refusal suppression
    • Style injection
    • Wikipedia with title

Tests and Documentation

No tests for templates

jl8771 avatar May 21 '24 19:05 jl8771

@microsoft-github-policy-service agree company="Centific"

jl8771 avatar May 21 '24 19:05 jl8771

Can you make the description and title more specific (e.g. which jailbreaks/papers)

rlundeen2 avatar May 21 '24 19:05 rlundeen2