Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

FEAT: Add nesting and prepend/append jailbreaks from papers #216

Merged
merged 5 commits into from
May 28, 2024

Conversation

jl8771
Copy link
Contributor

@jl8771 jl8771 commented May 21, 2024

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
Copy link
Contributor Author

jl8771 commented May 21, 2024

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

@rlundeen2
Copy link
Contributor

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

@jl8771 jl8771 changed the title FEAT: Add jailbreaks from papers FEAT: Add nesting and prepend/append jailbreaks from papers May 21, 2024
Copy link
Contributor

@rlundeen2 rlundeen2 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks really good!

@rlundeen2 rlundeen2 merged commit 0074d59 into Azure:main May 28, 2024
5 checks passed
@jl8771 jl8771 deleted the new branch July 1, 2024 18:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants