check_sec / README.md
huolongguo10's picture
Update README.md
a3658d7
|
raw
history blame
926 Bytes
---
license: openrail
datasets:
- huolongguo10/insecure
language:
- en
library_name: transformers
pipeline_tag: text-classification
tags:
- code
---
# check_sec
检查web参数安全性,支持多种payload(v0.0.4)
## 类型
```
LABEL_0: secure
LABEL_1: insecure(可能包含payload)
```
## 使用
```python
import transformers
from transformers import BertTokenizer, DataCollatorWithPadding
from transformers import AutoModelForSequenceClassification
tokenizer = BertTokenizer.from_pretrained('huolongguo10/check_sec')
model = AutoModelForSequenceClassification.from_pretrained('huolongguo10/check_sec', num_labels=2)
import torch
def check(text):
inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
predicted_class_id = logits.argmax().item()
print(f'{logits.argmax().item()}:{text}')
return 'secure' if predicted_class_id==0 else 'insecure'
```