#machine learning
Oct 2023
Label Differential Privacy via Aggregation
This paper demonstrates that aggregating labels from sub-sampled disjoint $k$-sized bags using i.i.d. weights allows for similar label-DP guarantees when aggregating labels over random disjoint bags, while preserving the utility of Lipschitz-bounded neural mse-regression tasks.
Anand Brahmbhatt, Rishi Saket, Shreyas Havaldar et al.
· arXiv.org · 1 citation
· ⚡1