Jailbreak heuristics #292
Merged
Jailbreak heuristics #292
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
…about threshold values in jailbreak_detection.md. Make threshold configurable. Add JailBreakDetectionConfig class and add to RailsConfigData Signed-off-by: Erick Galinkin <[email protected]>
… in jailbreaks check. Include info about usage in jailbreak_detection.md. Signed-off-by: Erick Galinkin <[email protected]>
Signed-off-by: Erick Galinkin <[email protected]>
drazvan
requested changes
Feb 6, 2024
There was a problem hiding this comment.
Looks good 👍 .
Apart from the comments above, there are a couple more things that should be added:
- Basic tests (which either mock the server, or use the in-process route suggested).
- Analysis of the performance, e.g., what's the latency this method adds? on a CPU, I assume on GPU it's much faster. What would be the throughput of the server? We just need to document this after we run some tests.
…lbreak heuristics documentation to guardrails-library.md. Update requirements.txt for jailbreak detection. Allow actions.py to run in-process. Add exception logging to request.py.
…n names Signed-off-by: Erick Galinkin <[email protected]>
…ary.md. Include GPU dockerfile, Dockerfile-GPU.
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Outdated suggestions cannot be applied.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.
Add jailbreak heuristics