Why it matters
March 23, 2026 - March 25, 2026
IEEE SaTML 2026 brought secure and trustworthy machine-learning research to the Technical University of Munich. The program addressed attacks and defenses, system and algorithm verification, ML privacy and forensics, interpretability and fairness, trustworthy data curation, and practical evaluation of learning systems.
My takeaway: SaTML is most valuable when papers make trust claims falsifiable. Record the threat model, security property, evaluation distribution, adaptive attacker, proof or empirical evidence, and artifact availability; avoid translating narrow benchmark robustness into broad claims about deployed-system safety.