You can deploy this model and start earning money today!

fredstrey/
deberta-v3-base-prompt-injection-v3

Name: deberta-v3-base-prompt-injection-v3
Availability: InStock

Views

No views yet

DeBERTa v3 — Prompt Injection PT-BR (SUFRAMA)

Fine-tuned version of protectai/deberta-v3-base-prompt-injection-v2 for prompt injection detection in Brazilian Portuguese, specialized for the SUFRAMA domain.

The fine-tuning dataset was built from three sources:

rogue-security/prompt-injections-benchmark — translated to Brazilian Portuguese.
xTRam1/safe-guard-prompt-injection — translated to Brazilian Portuguese.
Synthetic domain samples — generated from SUFRAMA domain documents and real chatbot interactions.

The first 8 of 12 DeBERTa encoder layers were frozen, keeping only the top 4 layers and the classification head trainable.