.png){kind=icon}
.png){kind=icon}
Return
Website categorization via design attribute learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cose.2021.102312.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Malicious software (malware) is a challenging cybersecurity threat, as it is often bundled with legitimate software and downloaded by na & iuml;v e users. A significant source of malware downloads is via crack websites that are used to circumvent copyright protection mecha-nisms. Crack websites often change URLs and IPs to avoid automatic detection; however, in many cases, they preserve specific visual designs that signal the website's function to poten-tial users (such as particular colors, text fonts, shapes, and sizes.). Website design features are numerous, have high dimensionality and complicated interactions, making categoriza-tion challenging. This study shows that straightforward machine learning models for cate-gorizing Crack and Malicious websites can considerably benefit from using design features. We report on two experiments based on unbalanced datasets and show that classification by using design features can reach a categorization accuracy of over 90% with an F1-score over 77% in some instances. Finally, we discuss the results in the context of developing in-telligent security mechanisms. (c) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Online learning
Crack websites
Malware
Website categorization
Website design elements
Cyber security
Human computer interaction
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.