Research Article
New Hybrid Features Selection Method: A Case Study on Websites Phishing
Table 2
Features score(s) and rank of our new method, IG, and Chi-square on the phishing dataset.
| Feature | Rank | Score | Normalized IG score | Rank | Score | Normalized Chi score | Combined IG and Chi score | New rank (IG + Chi) |
| having_IP_Address | 13 | 0.006 | 0.012024048 | 13 | 98 | 0.014657493 | 0.018958371 | 13 | URL_Length | 17 | 0.003 | 0.006012024 | 17 | 57 | 0.008525277 | 0.010431911 | 17 | Shortining_Service | 18 | 0.003 | 0.006012024 | 18 | 51 | 0.007627879 | 0.00971231 | 18 | having_At_Symbol | 20 | 0.002 | 0.004008016 | 20 | 31 | 0.004636554 | 0.00612877 | 20 | double_slash_redirecting | 23 | 0.001 | 0.002004008 | 23 | 16.5 | 0.002467843 | 0.00317904 | 23 | Prefix_Suffix | 3 | 0.123 | 0.246492986 | 5 | 1343 | 0.200867484 | 0.317972543 | 5 | having_Sub_Domain | 5 | 0.109 | 0.218436874 | 4 | 1595 | 0.238558181 | 0.323457375 | 4 | SSLfinal_State# | 1# | 0.499 | 1 | 1# | 6686 | 1 | 1.414213562 | 1# | Domain_registeration_length | 9 | 0.036 | 0.072144289 | 8 | 563 | 0.084205803 | 0.110884695 | 8 | Favicon | 29 | 0 | 0 | 29 | 0 | 0 | 0 | 29 | port | 24 | 0.0009 | 0.001803607 | 24 | 14.6 | 0.002183667 | 0.002832208 | 24 | HTTPS_token | 22 | 0.001 | 0.002004008 | 22 | 17.5 | 0.00261741 | 0.003296495 | 22 | Request_URL | 7 | 0.046 | 0.092184369 | 7 | 709 | 0.106042477 | 0.140509661 | 7 | URL_of_Anchor# | 2# | 0.477 | 0.955911824 | 2# | 5966 | 0.892312294 | 1.307665341 | 2# | Links_in_tags | 6 | 0.047 | 0.094188377 | 6 | 712 | 0.106491176 | 0.142168283 | 6 | SFH | 8 | 0.037 | 0.074148297 | 9 | 542 | 0.081064912 | 0.10986123 | 9 | Submitting_to_email | 26 | 0.0002 | 0.000400802 | 26 | 3.7 | 0.000553395 | 0.000683292 | 26 | Abnormal_URL | 19 | 0.002 | 0.004008016 | 19 | 40 | 0.00598265 | 0.007201132 | 19 | Redirect | 25 | 0.0002 | 0.000400802 | 25 | 4.5 | 0.000673048 | 0.000783349 | 25 | on_mouseover | 21 | 0.002 | 0.004008016 | 21 | 19 | 0.002841759 | 0.004913226 | 21 | RightClick | 27 | 0 | 0 | 27 | 1.7 | 0.000254263 | 0.000254263 | 27 | popUpWidnow | 30 | 0 | 0 | 30 | 0 | 0 | 0 | 29 | Iframe | 28 | 0 | 0 | 28 | 0.1 | | | 28 | age_of_domain | 11 | 0.01 | 0.02004008 | 11 | 163 | 0.0243793 | 0.031558756 | 11 | DNSRecord | 16 | 0.004 | 0.008016032 | 16 63 | 0.009422674 | 0.012371078 | 16 | | web_traffic | 4 | 0.1145 | 0.229458918 | 3 | 1712 | 0.256057433 | 0.343826707 | 3 | Page_Rank | 12 | 0.008 | 0.016032064 | 12 | 121 | 0.018097517 | 0.024177411 | 12 | Google_Index | 10 | 0.011 | 0.022044088 | 10 | 183 | 0.027370625 | 0.035143889 | 10 | Links_pointing_to_page | 15 | 0.004 | 0.008016032 | 15 | 66 | 0.009871373 | 0.012716162 | 15 | Statistical_report | 14 | 0.004 | 0.008016032 | 14 | 70 | 0.010469638 | 0.013185981 | 14 |
|
|