Date: March 17, 2026, 5:00 PM – 6:30 PM Location: Hasso Plattner Institute, Potsdam (Campus Kitchen One, Building L, Room L-1.02) Format: Talk & Discussion (In-person)
What is it about? Deepfakes are becoming increasingly realistic, making it harder to distinguish between genuine and generated content. In this guest talk, Jonas Bernhard (Machine Learning Engineer at Merantix Momentum) explores how deepfakes are created and what distinguishes “fake” from “real” images. He will present Clyravision as a concrete solution: a multi-agent system that combines various AI models to not only detect deepfakes but also make the detection process interpretable and transparent.
For whom? The talk is aimed at anyone interested in generative AI, media security, and technical approaches to combating disinformation—from developers to the general public.
Prerequisites The event is open to everyone. Binding registration is required.
Registration Participation is free of charge.
