Behavioral Authentication with Machine Learning (Sommersemester 2018)
Dozent: Prof. Dr. Christoph Meinel
(Internet-Technologien und -Systeme)
M.Sc. Christian Tietz
Passwords are used for securing computer systems for a long time. Nevertheless, people use short and weak passwords for their own accounts. One of the reasons is that humans are not good in memorizing long random strings. To solve this problem, the Secure Identity Lab of HPI is developing a system that does not rely on password but on human behavior, such as gait recognition. Our system in its current version can detect the gait of the user and determine the trust level, a probability that the user is also the owner.
This trust level is later sent to an identity provider (IDP) and forwarded to services for authentication.
There exist several requirements for ‘good’ biometrics and for ‘good’ authentication systems. In the case of biometrics these are e.g. “availability” of the biometric data in many situations or “acceptance” of the user that the data is collected.
In terms of authentication systems there are requirements for low error rates or resistances against several attacks, for example. Referring to our approach described above and the current level of research, a lot of questions are not answered yet.
In this seminar we want to look at several topics in terms of these requirements:
- Behavioral authentication based on typing
- Behavioral authentication in special situations like with injuries or for very old persons
- Architectures for Trust Level Exchange
- Benchmarking of behavioral authentication approaches
Please note that all of our topics are basically general proposals. Please feel free to join our seminar and share your own very special ideas in this field of research.
The grade of this course will be based on: two presentations, implementation and a paper.
Topic Presentation: 09.04. 2018 , 11:00 a.m., room H-E.51
Topic choice until 15.04.
Weekly meetings starting on 16.04. , every monday
Extended abstract: TBA
Intermediate presentation: TBA
Final presentation: TBA
- Semesterwochenstunden : 4
- ECTS : 6
- Benotet :
- Einschreibefrist : 18.04.2018
- Lehrform : S
- Belegungsart : Wahlpflicht
Studiengänge & Module
IT-Systems Engineering MA
- ISAE-Konzepte und Methoden
- ISAE-Techniken und Werkzeuge
- OSIS-Konzepte und Methoden
- OSIS-Techniken und Werkzeuge