urlbert-tiny-v3 Open-source Website Classification Model - Free Deployment for Precise Recognition of Four Types of Websites

Urlbert Tiny V3 Malicious Url Classifier

Developed by CrabInHoney

Lightweight BERT model fine-tuned specifically for URL classification tasks, capable of categorizing URLs as benign, phishing, malware, or defacement

Text Classification

Transformers

Supports Multiple LanguagesOpen Source License:Apache-2.0 #Lightweight BERT #Malicious URL Detection #Phishing Identification

Downloads 452

Release Time : 2/19/2025

Model Overview

Lightweight model based on BERT architecture for detecting and classifying malicious URLs, supporting identification of phishing sites, malware distribution sites, and defacement links

Model Features

Lightweight Design

Only 3.69 million parameters with a model weight size of 14.8MB, suitable for deployment in resource-constrained environments

High Accuracy

Overall accuracy of 98.37%, with F1 scores above 94% for all categories

Multi-Category Detection

Capable of simultaneously identifying phishing, malware, defacement, and benign URLs

Specialized Optimization

BERT variant optimized for URL structural characteristics to enhance URL classification effectiveness

Model Capabilities

URL Security Detection

Phishing Site Identification

Malware Link Detection

Defacement Link Identification

Real-Time URL Classification

Use Cases

Cybersecurity Protection

Browser Security Plugin

Integrated into browsers to detect the safety of visited URLs in real-time

Prevents users from accessing phishing or malicious websites

Email Security Filtering

Scans suspicious links in emails

Effectively identifies malicious links in phishing emails

Enterprise Security

Network Traffic Monitoring

Analyzes suspicious URL visits within corporate intranet traffic

Timely detection of employees accessing dangerous websites

🚀 URLBERT-Tiny-v3 Malicious URL Classifier

This is a lightweight version of BERT, specifically fine-tuned for classifying URLs into four categories: benign, phishing, malware, and defacement.

✨ Features

Specifically designed for URL classification, capable of distinguishing between benign, phishing, malware, and defacement URLs.
Lightweight, with only 3.69M parameters, making it efficient for practical applications.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import BertTokenizerFast, BertForSequenceClassification, pipeline
import torch

# Определение устройства (GPU или CPU)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Используемое устройство: {device}")

# Загрузка модели и токенизатора
model_name = "CrabInHoney/urlbert-tiny-v3-malicious-url-classifier"
tokenizer = BertTokenizerFast.from_pretrained(model_name)
model = BertForSequenceClassification.from_pretrained(model_name)
model.to(device)

# Создание pipeline для классификации
classifier = pipeline(
    "text-classification",
    model=model,
    tokenizer=tokenizer,
    device=0 if torch.cuda.is_available() else -1,
    return_all_scores=True
)

# Примеры URL для тестирования
test_urls = [
    "wikiobits.com/Obits/TonyProudfoot",
    "http://www.824555.com/app/member/SportOption.php?uid=guest&langx=gb",
]

# Маппинг меток на понятные названия классов
label_mapping = {
    "LABEL_0": "benign",
    "LABEL_1": "defacement",
    "LABEL_2": "malware",
    "LABEL_3": "phishing"
}

# Классификация URL
for url in test_urls:
    results = classifier(url)
    print(f"\nURL: {url}")
    for result in results[0]: 
        label = result['label']
        score = result['score']
        friendly_label = label_mapping.get(label, label)
        print(f"Класс: {friendly_label}, вероятность: {score:.4f}")

Example Output:

URL: wikiobits.com/Obits/TonyProudfoot
Класс: benign, вероятность: 0.9953
Класс: defacement, вероятность: 0.0000
Класс: malware, вероятность: 0.0000
Класс: phishing, вероятность: 0.0046

URL: http://www.824555.com/app/member/SportOption.php?uid=guest&langx=gb
Класс: benign, вероятность: 0.0000
Класс: defacement, вероятность: 0.0001
Класс: malware, вероятность: 0.9998
Класс: phishing, вероятность: 0.0001

📚 Documentation

Model Details

Property	Details
Model size	3.69M parameters
Tensor type	F32
Model weight size	14.8 MB
Base model	CrabInHoney/urlbert-tiny-base-v3
Dataset	Malicious URLs Dataset

Model Evaluation Results

The model was evaluated on a test set with the following classification metrics:

Class	Precision	Recall	F1-Score
Benign	0.987695	0.993717	0.990697
Defacement	0.988510	0.998963	0.993709
Malware	0.988291	0.960332	0.974111
Phishing	0.958425	0.930826	0.944423
Accuracy	0.983738	0.983738	0.983738
Macro Avg	0.980730	0.970959	0.975735
Weighted Avg	0.983615	0.983738	0.983627

📄 License

This model is licensed under the Apache-2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご