This website uses machine learning to detect if a given website is phishing or legitimate.
- Python 3.9.6
- beautifulsoup4 4.9.3
- Flask 1.1.2
- ipaddress 1.0.23
- urllib3 1.25.10
- tldextract 3.1.2
- whois 0.9.13
- scikit_learn 0.24.2
- numpy 1.21.2
- pandas 1.3.2
- lxml 4.5.0
- Extracts domain based features:
a. having_IP_Address
b. Redirect, Prefix_Suffix
c. having_sub_domain
d. Domain_registration_length
e. HTTPS_token
f. Request_URL
g. URl_of_Anchor
h. Links_in_tags
i. age_of_domain
j. DNSRecord - Extracts url based features:
a. URL_Length
b. having_At_Symbol
c. double_slash_redirecting
d. web_traffic
e. Shortening_Service - Extracts JS features:
a. Submitting_to_email
b. on_mouseover
c. RightClick
d. Iframe
e. Favicon
- Database to store searched queries.
- Removing saved queries after specific time, to keep a check on the legitimacy of the website.
To run this project, install libraries given above:
$ cd WaterPhish/
$ flask run