top of page

New paper: Website categorization via design attribute learning

May 27, 2021
1 min read

Eran had contributed to a new paper by the LAMBDA Lab headed by Prof. Irad Ben-Gal. The paper, by Doron Cohen, Or Naim, Eran Toch, and Irad Ben-Gal, suggests a new way to categorize

crack websites, which contain a mixture of harmless and malware software. You can download the paper from here. The basic observation is that crack websites need to balance two opposing requirements to successfully function: Escaping malware detection tools while signaling to users that they have free software for download. Therefore,  we hypothesize that in many cases, they preserve specific visual designs that signal the website's function to potential users (such as particular colors, text fonts, shapes, and sizes.)

The study shows that machine learning models for categorizing Crack and Malicious websites can considerably benefit from using design features.

We report on two experiments based on unbalanced datasets and show that

by using design features can reach a categorization accuracy of over 90% with an F1-score over 77% in some instances.  

 
 
 

Comments


wolfson1.jpg

Contact Us

The lab is located at the Faculty of Engineering, in the Wolfson building for Mechanical Engineering, in the School of Industrial & Intelligent Systems Engineering. To reach our building, enter the campus through Gate 14 on Klausner St., Gate 4 (always open) on George Wise St., or Gate 17. The Wolfson building is marked on the map below. You can also find it as building 34 on the official TAU map.

Chaim Levanon St 30 (Dr. George Wise Street for postal correspondence), Tel Aviv-Yafo, 6997801, Israel

Thanks for submitting!

© 2023 by Tel Aviv University. Proudly created with Wix.com

bottom of page