edaerer
/

promptwaf-path-traversal

Text Classification

prompt-injection

text-embeddings-inference

Model card Files Files and versions

edaerer commited on May 7

Commit

b3e4bb0

·

verified ·

1 Parent(s): 6292916

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ The model identifies prompts containing directory escape patterns (`../`, `..\\`
 - **Architecture**: BERT (Base)
 - **Task**: Binary Sequence Classification
-- **Training**: Fine-tuned on path traversal attack datasets
 - **Labels**:
   - `0` → Safe/Benign
   - `1` → Path Traversal Attack

 - **Architecture**: BERT (Base)
 - **Task**: Binary Sequence Classification
+- **Training Data**: Trained on a custom, internally curated path traversal dataset
 - **Labels**:
   - `0` → Safe/Benign
   - `1` → Path Traversal Attack