| # BERT Phishing Detection Model |
|
|
| This is a BERT-based model fine-tuned for phishing detection. The model can classify text/URLs as phishing or legitimate. |
|
|
| ## Model Details |
|
|
| - **Model Type**: BERT for Sequence Classification |
| - **Architecture**: BertForSequenceClassification |
| - **Problem Type**: Single Label Classification |
| - **Hidden Size**: 768 |
| - **Number of Layers**: 12 |
| - **Number of Attention Heads**: 12 |
| - **Max Position Embeddings**: 512 |
| - **Vocabulary Size**: 30,522 |
|
|
| ## Usage |
|
|
| ```python |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification |
| import torch |
| |
| # Load model and tokenizer |
| model_name = "th1enq/bert_checkpoint" |
| tokenizer = AutoTokenizer.from_pretrained(model_name) |
| model = AutoModelForSequenceClassification.from_pretrained(model_name) |
| |
| # Example usage |
| text = "Your text here" |
| inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512) |
| |
| with torch.no_grad(): |
| outputs = model(**inputs) |
| predictions = torch.nn.functional.softmax(outputs.logits, dim=-1) |
| predicted_class = torch.argmax(predictions, dim=-1) |
| ``` |
|
|
| ## Training |
|
|
| This model was fine-tuned on phishing detection data to classify text as phishing (1) or legitimate (0). |
|
|
| ## License |
|
|
| Please refer to the original BERT license and any applicable dataset licenses. |
|
|
