Repository navigation
fix: resolve stash conflict; non-Latin over-defense fix + Necent benc… - #3
Merged
Merged
Conversation
…hmarks Resolve a stash-pop conflict in src/tiers/l2.ts and tests/l2.test.ts: - Remove a duplicated scanSpecialTokens/scanAdversarialSuffix block left by an "accept both sides" resolution (was double-scoring special_token_injection). - Keep the run-based script_mixing fix and its intra-word interleaving test over the old whole-string-count behavior. Non-Latin over-defense fix (token-aware confusable folding + intra-word script_mixing) eliminates Russian/Georgian benign false positives without touching genuine-homoglyph or English behavior. Add Necent/llm-jailbreak-prompt-injection-dataset benchmarks (Tier 0 and Tier 0+1 local ML) and report. The 50k sample stays out of the repo (pointed at via NECENT_SAMPLE). README: correct decode-rescan entropy gate (>4.8 OR, not >4.3 AND), seed attack corpus count (23), and checkSync throw list (add embeddingCorpus). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…hmarks
Resolve a stash-pop conflict in src/tiers/l2.ts and tests/l2.test.ts:
Non-Latin over-defense fix (token-aware confusable folding + intra-word script_mixing) eliminates Russian/Georgian benign false positives without touching genuine-homoglyph or English behavior.
Add Necent/llm-jailbreak-prompt-injection-dataset benchmarks (Tier 0 and Tier 0+1 local ML) and report. The 50k sample stays out of the repo (pointed at via NECENT_SAMPLE).
README: correct decode-rescan entropy gate (>4.8 OR, not >4.3 AND), seed attack corpus count (23), and checkSync throw list (add embeddingCorpus).