Given a Brauer class on a K3 surface defined over a number field, I will prove that there exists infinitely many primes where the reduction of the Brauer class vanishes, under certain technical hypotheses. This answers a question of Frei--Hassett--Várilly-Alvarado. The proof relies on Arakelov intersection theory on integral models of GSpin Shimura varieties. The result of this talk is joint work with Davesh Maulik.