The goal of the project is to investigate in how far it is possible to identify the user
of a website based on tracked signals from keyboard and mouse only. If so, such technologies
could be used to increase the safety of web usage (e.g. match user login to signal profile, identify
possible hazardeous anonymous users in terms of their signal fingerprint). The problem itself
is a classical problem within machine learning, where the task is to design a test environment, gather
test data, design a suitable feature representation, identify suitable ML pipelines for a valid classification,and evaluate the results in realistic scenarios.
In case this would not find enough interest for a team project, this project proposal would be also offered (in reduced/modified form)
The project team for this project has already been selected, no additional applications are considered.
Advanced Machine Learning skills are required.
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.