Confidence in AI systems: Can we trust AI-based systems?
Abstract
The success of deep learning in many application domains has been nothing short of dramatic. This has brought the spotlight onto security and privacy concerns with machine learning (ML). I will give a high-level overview of the security and privacy concerns with AI-based systems. I will also briefly touch on protecting AI models against multiple concerns simultaneously, an important but hitherto insufficiently-explored problem.
Date and Location
22 April 2024, 16:15, Uni Engehalde, Engehaldestrasse 8, Room 107
Speaker
Prof. N. Asokan, University of Waterloo
N. Asokan is a professor of computer science and the David R. Cheriton Chair in Software Systems at the University of Waterloo's David R. Cheriton School of Computer Science. He is also an adjunct professor in the Department of Computer Science at Aalto University. In previous positions, he worked at the IBM Zurich Research Laboratory in Switzerland and at the Nokia Research Center in Helsinki.