Skip to content

Commit aaa584e

Browse files
committed
fix: removed leftover conflict marker and duplicate paragraph
1 parent b3852b4 commit aaa584e

1 file changed

Lines changed: 0 additions & 2 deletions

File tree

‎README.md‎

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -83,8 +83,6 @@ signal — only genuine zero-width/bidi control characters and mixed-script
8383
homoglyph smuggling are flagged. Robust multi-language injection detection is
8484
tracked as a separate work item.
8585

86-
On the neuralchemy prompt-injection set, regex-only detection reaches **F1 0.56 / recall 0.39** — a fast first line, not sufficient alone. Adding the ML span model (`Guard(model="tiny")`) takes that to **F1 0.99 / recall 0.98**, and lifts recall on *indirect* injection from **0.05 → 0.91**. False-positive rate stays under 1% on the injection set (2.1% on a separate hard-benign corpus). Full tables, methodology, and honest caveats: [`sdk/docs/BENCHMARKS.md`](sdk/docs/BENCHMARKS.md). Per-axis model metrics (including failure modes) are on the [model card](https://huggingface.co/Unplug-AI/unplug-tiny-v1).
87-
>>>>>>> b27d848 (docs: replaced remaining Guard.with_tiny() references with Guard(model='tiny'))
8886

8987
## Agent host checklist
9088

0 commit comments

Comments
 (0)