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

Tree of Attacks #446

Merged
merged 14 commits into from
Feb 20, 2024
Merged

Tree of Attacks #446

merged 14 commits into from
Feb 20, 2024

Commits on Jan 29, 2024

  1. Initial commit containing full, untested implementation for tree of a… 

    …ttacks.

Updated requirements.txt to include numpy.
    @erickgalinkin
    erickgalinkin committed Jan 29, 2024
    Configuration menu
    Copy the full SHA
    b5fe604 View commit details
    Browse the repository at this point in the history

Commits on Jan 31, 2024

  1. Fix issues with generation, create OpenAIConvGenerator class, replace… 

    … ast.literal_eval with regular expression. Add small handful of jailbreaks successful against gpt-3.5-turbo and gpt-4.
    @erickgalinkin
    erickgalinkin committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    4a2cad1 View commit details
    Browse the repository at this point in the history

  2. Add TAP probe

    @erickgalinkin
    erickgalinkin committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    97c96be View commit details
    Browse the repository at this point in the history

Commits on Feb 2, 2024

  1. add TAP doc; replace Path with basedir; black

    @leondz
    leondz committed Feb 2, 2024
    Configuration menu
    Copy the full SHA
    cdd0e08 View commit details
    Browse the repository at this point in the history

Commits on Feb 5, 2024

  1. reflect req updates in project toml

    @leondz
    leondz committed Feb 5, 2024
    Configuration menu
    Copy the full SHA
    68972bc View commit details
    Browse the repository at this point in the history

Commits on Feb 12, 2024

  1. Add docstrings to tap_main.py and generator_utils.py.

    @erickgalinkin
    erickgalinkin committed Feb 12, 2024
    Configuration menu
    Copy the full SHA
    8e5ecae View commit details
    Browse the repository at this point in the history

  2. Modify TAP generation in tap_main.py to work with probes. Add pruning… 

    … as a parameter in run_tap function. Rename current TAPProbe to TapCachedProbe. Add TAPProbe and PAIRProbe.
    @erickgalinkin
    erickgalinkin committed Feb 12, 2024
    Configuration menu
    Copy the full SHA
    2fe261b View commit details
    Browse the repository at this point in the history

Commits on Feb 16, 2024

  1. Merge changes

    @erickgalinkin
    erickgalinkin committed Feb 16, 2024
    Configuration menu
    Copy the full SHA
    58808d2 View commit details
    Browse the repository at this point in the history

  2. Fix issues with generation, create OpenAIConvGenerator class, replace… 

    … ast.literal_eval with regular expression. Add small handful of jailbreaks successful against gpt-3.5-turbo and gpt-4.
    @erickgalinkin
    erickgalinkin committed Feb 16, 2024
    Configuration menu
    Copy the full SHA
    467f1a7 View commit details
    Browse the repository at this point in the history

  3. add TAP doc; replace Path with basedir; black

    @leondz @erickgalinkin
    leondz authored and erickgalinkin committed Feb 16, 2024
    Configuration menu
    Copy the full SHA
    b4a9227 View commit details
    Browse the repository at this point in the history

  4. Merge branch 'main' into tree-of-attacks

    @erickgalinkin
    erickgalinkin authored Feb 16, 2024
    Configuration menu
    Copy the full SHA
    013618e View commit details
    Browse the repository at this point in the history

Commits on Feb 20, 2024

  1. black; add local path prefix (.) to modules in resources/tap

    @leondz
    leondz committed Feb 20, 2024
    Configuration menu
    Copy the full SHA
    ceb935b View commit details
    Browse the repository at this point in the history

  2. lazyload run_tap; rm Probe from names

    @leondz
    leondz committed Feb 20, 2024
    Configuration menu
    Copy the full SHA
    8e5ffd3 View commit details
    Browse the repository at this point in the history

  3. link TAP doc from probes.rst; demystify doc test for this

    @leondz
    leondz committed Feb 20, 2024
    Configuration menu
    Copy the full SHA
    43b80f1 View commit details
    Browse the repository at this point in the history