In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning. (arXiv:2209.10732v1 [cs.LG])

When learning from sensitive data, care must be taken to ensure that training
algorithms address privacy concerns. The canonical Private Aggregation of
Teacher Ensembles, or PATE, computes output labels by aggregating the
predictions of a (possibly distributed) collection of teacher models via a
voting mechanism. The mechanism adds noise to attain a differential privacy
guarantee with respect to the teachers' training data. In this work, we observe
that this use of noise, which makes PATE predictions stochastic, enables new
forms …

differential privacy privacy truth vote