Skip to main content

Table 2 A list of 30 distinct features

From: Development of anti-phishing browser based on random forest and rule of extraction framework

S.No

Features

Conditions

Result

1.

IP Address

Domain Part of URL contains IP Address

Phishing

Domain Part of URL doesn’t contain IP Address

Legitimate

2.

Length of URL

Length of URL below 54

Legitimate

Length of URL greater or equal to 54

Suspicious

Length of URL lesser or equal to 75

Phishing

3.

Shortening Services

Very Short URL

Phishing

Normal URL

Legitimate

4.

‘@’ Symbol

Existence of ‘@’ character in URL

Phishing

Absence of ‘@’ character in URL

Legitimate

5.

Double slash forwarding

Position of Last ‘// in URL is below 7

Phishing

Position of Last ‘// in URL is above 7

Legitimate

6.

Prefix and Suffixes

Existence of ‘−’ character in Domain name

Phishing

Absence of ‘−’ character in Domain name

Legitimate

7.

Sub Domain

No. of Dots equal to one in Domain Part of URL

Legitimate

No. of Dots equal to two in Domain Part of URL

Suspicious

No. of Dots greater than two in Domain Part of URL

Phishing

8.

SSL final Certificate

Using https by Trusted providers and Certificate Age should be greater than or equal to 1 Year

Legitimate

Using https with Non-Trusted providers

Suspicious

Using https by Non-Trusted providers and Certificate Age lesser than to 1 Year

Phishing

9.

Domain registration length

Expiry date of Domains lesser or equal to 1 year

Phishing

Expiry date of Domains greater than 1 year

Legitimate

10.

Favicon

Favicon retrieved from External source

Phishing

Favicon retrieved from Internal source

Legitimate

11.

Non-Standard Ports

Port No. has Preferred Status

Phishing

Port No. doesn’t have Preferred Status

Legitimate

12.

“HTTPS” token

Domain section with HTTP token

Phishing

Domain section without HTTP token

Legitimate

13.

URL Requests

Percent of request URL lesser than 22%

Legitimate

Percent of request URL is greater than or equal to 22% and lesser than 61%

Suspicious

Percent of request URL is greater than 61%

Phishing

14.

URL with anchor

Percent of request URL lesser than 31%

Legitimate

Percent of request URL is greater than or equal to 31% and lesser than 67%

Suspicious

Percent of request URL is greater than 67%

Phishing

15.

Tags containing Links

Percent of Links in “Meta”,” Link” and “Script lesser than 17%

Legitimate

Percent of Links in “Meta”,” Link” and “Script” is greater than or equal to 17% and lesser than 81%

Suspicious

Percent of Links in “Meta”,” Link” and “Script” is greater than 81%

Phishing

16.

Server Form Handler-SFH

“Is Empty” or “about: blank” in SFH

Phishing

SFH forwards to another Domain

Suspicious

SFH doesn’t contain “Is Empty” or “about: blank” or doesn’t forwards to another domain

Legitimate

17.

Submitting to email

“mail()” services usage

Phishing

Non-usage of “mail()”

Legitimate

18.

Abnormal URL

URL without Hostname

Phishing

URL with Hostname

Legitimate

19.

Webpage Redirect

Page redirect is lesser than or equal to one

Phishing

Page redirect is greater than or equal to two and less than four

Suspicious

Page redirect is greater than four

Legitimate

20.

On mouse over

Change in status bar with mouse over

Phishing

No Change in status bar with mouse over

Legitimate

21.

Mouse right clicks

Disabled Right Click

Phishing

Enabled Right Click

Legitimate

22.

Browser Pop up

Browser Popups with text boxes

Phishing

Browser Popups without text boxes

Legitimate

23.

Iframe

Webpage with usage of iframe

Phishing

Webpage without the use of iframe

Legitimate

24.

Age of domain

Domain age greater than 6 months

Phishing

Domain age lesser than 6 months

Legitimate

25.

DNS Record

Domain without DNS record

Phishing

Domain with DNS record

Legitimate

26.

Web traffic

webpage rank less than or equal to 100,00

Legitimate

webpage rank greater than 100,00

Suspicious

webpage rank greater than 100,000

Phishing

27.

Page Rank

Page Rank less than 0.2

Phishing

Page Rank greater than 0.2

Legitimate

28.

Google Index

Webpage without google index

Phishing

Webpage with google index

Legitimate

29.

Links pointing to page

No. of Links Pointing to Webpage is zero

Phishing

No. of Links Pointing to Webpage is less than or equal to two

Suspicious

No. of Links Pointing to Webpage is greater than two

Legitimate

30.

Statistical analysis report

Host having topmost Phishing IP Addresses

Phishing

Host without topmost Phishing IP Addresses

Legitimate