Contextual mapping of web-pages, and generation of fraud-relatedness score-values
Devices, systems, and methods of contextual mapping of web-page elements and other User Interface elements, for the purpose of differentiating between fraudulent transactions and legitimate transactions, or for the purpose of distinguishing between a fraudulent user and a legitimate user. User Interface elements of a website or webpage or application or other computerized service, are contextually analyzed. A first User Interface element is assigned a low fraud-relatedness score-value, since user engagement with the first User Interface element does not create a security risk or a monetary exposure. A second, different, User Interface element is assigned a high fraud-relatedness score-value, since user engagement with the second User Interface element creates a security risk or a monetary exposure. The fraud-relatedness score-values are taken into account, together with user-specific behavioral characteristics, in order to determine whether to generate a possible-fraud notification, or as part of generating a possible-fraud score for a particular set-of-operations.
1. A method comprising:
(a) automatically analyzing content of a banking or retailer website, by performing:
analyzing a log of historical transactions that are known to be fraudulent;
identifying in said log a first Graphical User Interface (GUI) element that is typically clicked by cyber-attackers as part of cyber-attacks;
identifying in said log a second Graphical User Interface (GUI) element that is typically not clicked by cyber-attackers as part of cyber-attacks;
constructing a lookup table that indicates that the first GUI element is typically clicked by cyber-attackers as part of cyber-attacks, and that further indicates that the second GUI element is typically not clicked by cyber-attackers as part of cyber-attacks;
(b) monitoring interactions of a user with said banking or retailer website via one or more input units of an end-user device, and detecting one or more user interactions that indicate a possibly-fraudulent activity based on one or more pre-defined threshold parameters;
(c) if said possibly-fraudulent activity that was detected in step (b), is a click of said user on the first GUI element, then activating a fraud-mitigation unit;
(d) if said possibly-fraudulent activity that was detected in step (b), is a click of said user on the second GUI element, then maintaining said fraud-mitigation unit deactivated;
wherein the method further comprises:
generating a security-exposure map of on-screen GUI elements of said banking or retailer website,
by generating a first indication that user-engagement with a first particular on-screen GUI element on a particular web-page of said banking or retailer website creates a potential security risk for said banking or retailer website,
and by generating a second indication that user-engagement with a second particular on-screen GUI element on said particular web-page of said banking or retailer website does not create a potential security risk for said banking or retailer website.
2. The method of claim 1 , comprising:
generating said fraud-exposure map of on-screen GUI elements of said banking or retailer website,
by generating a first additional indication that user-engagement with a first particular on-screen GUI element on a specific web-page of said banking or retailer website creates a potential fraud risk for said banking or retailer website,
and by generating a second additional indication that user-engagement with a second particular on-screen GUI element on said specific web-page of said banking or retailer website does not create a potential fraud risk for said banking or retailer website.
3. The method of claim 1 ,
wherein web-pages of said banking or retailer website are HTML-based pages that are accessible through a web browser.
4. The method of claim 1 ,
wherein web-pages of said banking or retailer website are components of a native mobile application.