German researchers find medical AI models vulnerable to attacks that expose patient training data with near-perfect accuracy; underrepresented groups at highest risk of identification despite anonymization.

Medical diagnosis AIs can be tricked into telling whose data trained them

AI models used to help diagnose medical conditions have a problem: They’re ready and willing to identify patients whose data was used to train them.German researchers reported in a Nature paper published Wednesday that discriminative AI models - those used to classify data and make predictions about new inputs based on their training sets - are particularly susceptible to membership inference attacks (MIAs) that query the models in an attempt to figure out whether a particular datapoint is inclu...