Recognition of web users with the aid of biometric user model

摘要

Methods aimed at recognition of users are able to identify browsers or machines, but cannot distinguish physical persons. Multiple identities of single users are common on the Internet and this phenomenon decreases trustfulness of presented content as well as quality of provided services. This paper proposes a novel method for recognition of persons on the Web using input device usage patterns (keyboard, computer mouse, touchscreen), behavioral biometrics. The essential part of this method is a biometric component attached to the user model of an information system serving as a biometric identifier. The recognition of users relies in matching these components, specifically comparing values distribution shapes, which are characterizing users. The paper presents results of the method performance, which were obtained in a series of experiments focused on different aspects of evaluation (recognition rate, scalability, etc.). More specifically, a conducted case study shows application of the method to solve an issue in website visits analysis caused by erasing cookies.