37ecd27608480aa3569a511a638ca74f-Supplemental.pdf

Tables 3 and 4 summarize hyperparameters for P A TE-FM and ALIBI respectively. Table 3: P A TE-FM (Algorithms 1 and 2) hyperparameters for select accuracy levels. By repeating this game multiple times, we can estimate the adversary's success rate and convert this The probability is taken over the bit b, the randomness of the mechanism M and the algorithm A. Theorem B.1. It now remains to be seen how we can bound the adversary's correct guessing rate "canaries", we can compute a lower bound on the adversary's We can improve the tightness of this bound further. The adversary simply looks at the model's confidence on (Game 3).