Tree of Attacks #446
Merged
Tree of Attacks #446
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ttacks. Updated requirements.txt to include numpy.
|
Need to test the code, run generation, and write probes. |
… ast.literal_eval with regular expression. Add small handful of jailbreaks successful against gpt-3.5-turbo and gpt-4.
|
replaced pathlib call w/. garak._config.basedir also - is there an interfaces to running full TAP locally via the attack manager? it looks like TAPProbe uses a cached set, which is great for getting off the gorund, but it'd be good to include a probe that runs full TAP |
I'll update the probe with a |
… as a parameter in run_tap function. Rename current TAPProbe to TapCachedProbe. Add TAPProbe and PAIRProbe.
… ast.literal_eval with regular expression. Add small handful of jailbreaks successful against gpt-3.5-turbo and gpt-4.
leondz
approved these changes
Feb 20, 2024
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Initial commit containing full, untested implementation for tree of attacks.
Updated requirements.txt to include numpy.