Online Edition

September 28-30


Tomasz Bąk

Head of Machine Learning

Poland, Digital Fingerprints


Tomasz Bąk is the Head of Machine Learning in Digital Fingerprints, a company which provides a tool that would defend every user of the critical service from the digital hijack. It it based on behavioral biometrics data from keyboard, mouse, touchpad and mobile (in progress). He has completed his PhD in 2018 from University of Economics in Katowice in the area of spatial sampling. He has published several papers in reputed journals and in the same gathered almost 10 years of experience in developing ML & Data Science solutions for business.


From Internet Access Devices Usage to Behavioural Model

The way of using mouse, keyboard, tablet or phone can be a great source of the information about user behaviour. Data can be gathered from a spectrum of sensors built into these devices. Then this data can be transferred into features which characterize user, like manner of typing, speed of cursor or mouse movement curve. This presentation will focus on how to use those features to build behavioural model which will be unique and adjusted to each of thousends of customers. This problem has some important additional aspects. For one user several different models can be built, therefore some aggregation methods has to be delivered. Some of data has to be anonymized. Continuous authentication is excepted by business. These factors define important limitations for models productionization. They will also be discussed.

Session Keywords

🔑 Big Scale Model Training
🔑 Behavioral biometrics
🔑 AI

« Back