Researchers at Ben-Gurion University of the Negev (BGU) presented a new artificial intelligence technique that could protect medical imaging systems from hacking and human errors at the 2020 International Conference on Artificial Intelligence in Medicine (AIME) on Aug. 26. Their innovative solution uses a dual-layer architecture that screens for two different types of anomalous instructions to capture those that are always unusual or outside of safe ranges and those that are inappropriate in the specific context.