Secrets Sentinel — xsmall-c2p-v1 (deberta-v3-xsmall (c2p only))
Variant of hypn05/secrets-sentinel Architecture: deberta-v3-xsmall (c2p only) · Parameters: 70M · Speed: 5.3× vs base · pos_att_type:
c2p only (p2c dropped at init)
Experimental variant. c2p-only position attention (p2c weights dropped before fine-tuning). Full fine-tune on data_v10. Fastest variant but 5 false positives on short Terraform identifiers (e.g. identifier = "mydb") vs 0 for xsmall-v1. Use xsmall-v1 for production; this variant is for research/speed benchmarking.
Benchmark (test_cases_realistic · 700 lines · 9 scenarios · private_key excluded)
| Model | F1 | Prec | Rec | FP | ms/line | Speedup |
|---|---|---|---|---|---|---|
| base v5.0.0 (reference) | 1.0000 | 1.0000 | 1.0000 | 0 | 0.938ms | 1× |
| xsmall-c2p-v1 (this model) | see notes | — | 1.0000 | see notes | ~5.3× faster | 5.3× |
Usage
from transformers import pipeline
detector = pipeline("text-classification", model="hypn05/secrets-sentinel-xsmall-c2p")
lines = [
"AWS_SECRET_ACCESS_KEY = 'wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY'",
"password = os.environ.get('DB_PASSWORD')",
"uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef",
"DB_PASSWORD=null",
]
for line, result in zip(lines, detector(lines)):
label = "SECRET" if result["label"] == "LABEL_1" else "safe "
print(f"[{label}] {result['score']:.1%} {line[:70]}")
Expected output:
[SECRET] 100.0% AWS_SECRET_ACCESS_KEY = 'wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY'
[safe ] 0.0% password = os.environ.get('DB_PASSWORD')
[safe ] 0.0% uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef
[safe ] 0.0% DB_PASSWORD=null
Parent model
See hypn05/secrets-sentinel for full documentation, integration examples (pre-receive hooks, GitHub Actions, pre-commit), training data details, and complete benchmark numbers across all variants.