https://github.com/farzeennimran/fake-website-detection
AI to detect malacious websites using ML and DL models
https://github.com/farzeennimran/fake-website-detection
artificial-intelligence data-science deep-learning detection-model fake-website machine-learning malcious-files python3
Last synced: 3 months ago
JSON representation
AI to detect malacious websites using ML and DL models
- Host: GitHub
- URL: https://github.com/farzeennimran/fake-website-detection
- Owner: farzeennimran
- Created: 2025-01-17T08:33:16.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-01-25T23:09:16.000Z (over 1 year ago)
- Last Synced: 2025-03-14T02:11:57.365Z (over 1 year ago)
- Topics: artificial-intelligence, data-science, deep-learning, detection-model, fake-website, machine-learning, malcious-files, python3
- Language: Jupyter Notebook
- Homepage:
- Size: 1.65 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Fake-website-detection
Growing phishing attacks represent a serious challenge to the security of the computing
environment-the large number of spurious websites motivated by deception and to extract
sensitive information from individuals. This project proposes to reduce by exploring the transition from
machine learning approaches to deep learning approaches for fake website detection.
Deep learning models, by their very nature, can automatically extract features and,
therefore, are capable of identifying complex patterns and nuanced relationships within the
data, which would otherwise be missed by traditional techniques. Based on methodologies
like CNNs and RNNs etc, the proposed system efficiently captures complicated, deep features
from the URLs and web content, therefore augmenting its ability to detect sophisticated
phishing techniques. Enhancement of both the precision in detection and model adaptability
to the evolving phishing tactics are considered as priorities. A comprehensive assessment
shows that deep learning significantly outperforms traditional approaches, thereby
facilitating a more meaningful sense of improvement in security measures in the fight against
phishing attacks