URL Phishing Detector
Model Description
Random Forest ๋ชจ๋ธ๋ก URL์ ์ ์ฑ ์ฌ๋ถ๋ฅผ ํ๋จํ๋ ์ด์ง ๋ถ๋ฅ๊ธฐ์ ๋๋ค.
ํ๋ก์ ํธ: ์ค๋ฏธ์ฑ ํ์ง ์์คํ
(OCR/QR + URL ์ํ ํ๋จ)
์์ฑ์: ์ด๊ฒฝ์ค
Performance
- Accuracy: 100.00%
- Precision: 100.00%
- Recall: 100.00%
- F1-Score: 100.00%
Features
30๊ฐ์ URL ํน์ง์ ์ฌ์ฉํฉ๋๋ค:
- URL ๊ตฌ์กฐ (๊ธธ์ด, ํน์๋ฌธ์, ํ์ดํ ๋ฑ)
- ๋๋ฉ์ธ ํน์ฑ (IP ์ฃผ์, ์ํธ๋กํผ, TLD ๋ฑ)
- ์ฝํ ์ธ ํน์ง (HTTPS, ์์ฌ ํค์๋, ๋ธ๋๋ ๋ถ์ผ์น ๋ฑ)
Usage
import joblib
from huggingface_hub import hf_hub_download
# ๋ชจ๋ธ ๋ค์ด๋ก๋
model_path = hf_hub_download(repo_id="kanell0304/url-phishing-detector", filename="url_classifier.pkl")
model = joblib.load(model_path)
# ์์ธก
# features = extract_features(url) # ํน์ง ์ถ์ถ ํ์
# prediction = model.predict([features])
Training Data
- Phishing URLs: PhishTank, URLhaus
- Benign URLs: Tranco Top Sites
Limitations
- ์๋ก์ด ํผ์ฑ ํจํด์ ๋ํ ์ง์์ ์ธ ์ฌํ์ต ํ์
- ๋จ์ถ URL์ ํ์ฅ ํ ๋ถ์ ๊ถ์ฅ
Citation
@misc{url-phishing-detector,
author = {์ด๊ฒฝ์ค},
title = {URL Phishing Detector},
year = {2025},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/kanell0304/url-phishing-detector}}
}
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support