JHC04567
/

spid-deberta-base

Text Classification

prompt-injection

prompt-injection-detection

Eval Results (legacy)

text-embeddings-inference

Model card Files Files and versions

JHC04567 commited on May 31

Commit

b86d0a9

·

verified ·

1 Parent(s): e0542a2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -52,7 +52,7 @@ model-index:
 The key innovation is **fragment-based detection**: SPID splits input into fragments and classifies each independently, catching compound attacks where a malicious instruction hides behind a benign prefix.
-> Full pipeline, training code, and demo videos: **[GitHub repository](https://github.com/JHC56/spid)**
 ## Demo

 The key innovation is **fragment-based detection**: SPID splits input into fragments and classifies each independently, catching compound attacks where a malicious instruction hides behind a benign prefix.
+> > Full pipeline, training code, and demo videos: **[GitHub repository](https://github.com/JHC56/spid)** — If you find this useful, a ⭐ on GitHub is appreciated!
 ## Demo