Speaker

Dr. Adria Perez-Rovira

Senior Research Scientist

Daon

Talk

Is that really you? ML solutions for the real world problems of identity verification

Biography

Dr. Adria Perez-Rovira is a former medical image specialist who developed machine learning solutions to automatically extract information from medical images (CTs, MRI, retinal scans, etc.) in order to better diagnose and quantify disease progression. Now, as a senior biometric researcher in Daon, he is part of a team of researchers who use the latest machine learning tools to figure out what makes you unique in order to develop novel biometric authentication methods that are already making authentication systems more secure and less cumbersome.

Excerpt

Biometric authentication systems are plentiful in our daily routines, from unlocking our phone with a fingerprint or image of the face to validating the identity of a student by their typing behaviour during an online exam. Most, if not all, of these systems leverage large amounts of data and machine learning algorithms to correctly identify and verify the identity of the user. But what happens when someone prints a high resolution image of your face, and presents it in front of a camera to access your bank account?