You can deploy this model and start earning money today!

clawdia-chan/
balanced-deberta

Name: balanced-deberta
Availability: InStock

safetensors

clawdia-chan/prompt-guard-v2

mit

Views

No views yet

Balanced DeBERTa Prompt Guard

Fine-tuned DeBERTa-v3-base for prompt injection and jailbreak detection.

Model Details

Base Model: microsoft/deberta-v3-base
Training Data: 536 samples (prompt-guard-v2 dataset)
- 417 malicious (78%)
- 119 benign (22%)

Dataset Categories (30+)

Category	Count
prompt_injection	80+
jailbreak	70+
flip_attack	30+
encoding_attack	50+
indirect_injection	40+
role_override	30+
privilege_escalation	20+
agent_chaining	20+
memory_poisoning	15+
vector_poisoning	15+
xss_attempt	15+
sql_injection	10+
benign	119

Supported Threats (15+ types)

Direct/Indirect Prompt Injection
FlipAttack (character swapping)
Jailbreak (DAN, role-play)
Encoding Attacks (Base64, Hex, URL, HTML, Unicode)
Multi-language jailbreak (中, 日, 韓, 西, 独, 露, etc.)
RAG/Vector Poisoning
Agent Chaining Attacks
Memory Poisoning

Usage

python

from transformers import AutoModelForSequenceClassification, AutoTokenizer
model_name = "clawdia-chan/balanced-deberta"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)