Add Magic Words and DRIFT papers - #2
Open
WhymustIhaveaname wants to merge 2 commits into
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds two papers to Security & Privacy, both in scope per the section's own framing ('related to LLM and LLM agents'). Under Adversarial Attacks: Magic Words (arXiv 2501.18280), a jailbreak that exploits skewed embedding-model output distributions to bypass safety guardrails. Under Inspection: DRIFT (arXiv 2601.14210), which trains a lightweight probe on mid-layer hidden states to flag low-confidence/untruthful generations in parallel with decoding, in the same vein as Inference-Time Intervention and Overthinking the Truth already listed there.