The paper “Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment” by Xaver Fink (RWTH & CERN), Borja Fernandez Adiego, Daniele Mirarchi, Eloise Matheson, Álvaro García González, Gianmarco Ricci (all CERN), Joost-Pieter Katoen has been accepted for presentation at the 18th NASA Formal Methods Symposium (NFM 2026). The paper analyzes and improves the adversarial robustness of a convolutional neural network (CNN) that assists crystal-collimator alignment at the Large Hadron Collider (LHC) at CERN by classifying a beam-loss monitor (BLM) time series during crystal rotation.