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.

Sign up for GitHub

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

Jump to bottom

[DRAFT ] - Simple Adaptive Jailbreaking #537

Draft
wants to merge 7 commits into
base: main
Choose a base branch
from
Draft

[DRAFT ] - Simple Adaptive Jailbreaking #537

wants to merge 7 commits into from

Commits on Sep 24, 2024

  1. adding simple adaptive attack orchestrator, prompt template and varia… 

    …bles to expose logprobs in openai chat targets
    jonesdaniel committed Sep 24, 2024
    Configuration menu
    Copy the full SHA
    d1ad1ca View commit details
    Browse the repository at this point in the history

Commits on Oct 7, 2024

  1. exploring API for exposing logprobs in gpto

    donebydan committed Oct 7, 2024
    Configuration menu
    Copy the full SHA
    38a380c View commit details
    Browse the repository at this point in the history

Commits on Nov 4, 2024

  1. merging main and handling conflicts ready for new implementation

    donebydan committed Nov 4, 2024
    Configuration menu
    Copy the full SHA
    6b73911 View commit details
    Browse the repository at this point in the history

Commits on Nov 7, 2024

  1. Exposing logprobs. Implemented random search with e2e logic in _proce… 

    …ss_conversation_stream. Adding prompt templates.
    donebydan committed Nov 7, 2024
    Configuration menu
    Copy the full SHA
    c9b07d9 View commit details
    Browse the repository at this point in the history

  2. slight logging info change

    donebydan committed Nov 7, 2024
    Configuration menu
    Copy the full SHA
    91ff8b9 View commit details
    Browse the repository at this point in the history

Commits on Nov 8, 2024

  1. slight clean up, removing inheritance from PAIROrchestrator, correcti… 

    …ng logprobs exposed (not toplogprobs)
    donebydan committed Nov 8, 2024
    Configuration menu
    Copy the full SHA
    722b0e0 View commit details
    Browse the repository at this point in the history

  2. fixing max logprobs updates. Leaving TODO for non logprob call

    donebydan committed Nov 8, 2024
    Configuration menu
    Copy the full SHA
    967ef9e View commit details
    Browse the repository at this point in the history