Added token smugging probe module #1192
Open
Conversation
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Implements 1141
Added
probes.smugglingmodules that attempts to obfuscate instructions into the LLM. Three probes implemented:Base64: encodes the instruction as base64 and asks the LLM to decode and respond.HypotheticalResponse: gets the LLM to replace a hypothetical response with instructions list.FunctionMasking: gets LLM to predict masked token and then use that to respond.Verification
garak -m --model_type mistral --model_name mistral-large-latest --probes smuggling.Base64,smuggling.HypotheticalResponse,smuggling.FunctionMasking